Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    scientifical and technical terms related to experimental methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense verbs followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    actions performed using methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.65
    TagMode
    -0.58
     BaseModel
    -0.49
    sizeCache
    -0.49
     esprits
    -0.46
     pleaſure
    -0.43
     Vikipedi
    -0.42
     davvero
    -0.42
    dafx
    -0.40
    protoimpl
    -0.40
    POSITIVE LOGITS
    逅
    0.49
    oneofs
    0.47
    <?
    0.47
     extensively
    0.46
     providing
    0.44
    findpost
    0.44
     several
    0.43
    postsleuth
    0.43
    ある
    0.43
    ximately
    0.42
    Act Density 4.408%

    No Known Activations