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

    Neuronpedia

    INDEX
    Explanations

    phrases that express contemplation or reflection on a subject

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

    thinking about how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.60
     مشين
    -0.58
     arşivlendi
    -0.57
    лтамалар
    -0.47
    ientras
    -0.47
     credere
    -0.44
     wied
    -0.43
    BagConstraints
    -0.41
     zoude
    -0.41
     dezelve
    -0.40
    POSITIVE LOGITS
     ways
    0.66
    География
    0.54
     WAYS
    0.51
     maneras
    0.47
     how
    0.44
     kysy
    0.44
     connexes
    0.42
     Ways
    0.42
    instancetype
    0.42
    caref
    0.42
    Act Density 0.012%

    No Known Activations