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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to personal involvement or identification

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

    I am, We remark, We choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.46
    httphttps
    -0.44
    afficheront
    -0.44
    protoimpl
    -0.40
    fromnode
    -0.39
    ynb
    -0.38
    photobucket
    -0.37
    Izvori
    -0.36
    kuuta
    -0.36
    Manbalar
    -0.35
    POSITIVE LOGITS
    ModelSerializer
    0.52
    rival
    0.48
    AndEndTag
    0.47
    SaveVideo
    0.47
     getItemId
    0.46
    Initializable
    0.46
    BeginInit
    0.46
    juri
    0.45
    CodedInputStream
    0.44
     columnIndex
    0.44
    Act Density 0.004%

    No Known Activations