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

    Neuronpedia

    INDEX
    Explanations

    Specifications/Descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Studi
    -0.07
     petition
    -0.06
     Bart
    -0.06
    Util
    -0.06
     vfs
    -0.06
     raping
    -0.06
     Vend
    -0.06
    files
    -0.06
     screening
    -0.06
    酒
    -0.06
    POSITIVE LOGITS
    くらい
    0.06
     statistic
    0.06
    _nama
    0.06
     Participant
    0.06
    Inflater
    0.06
     λεπ
    0.06
    .savetxt
    0.06
     lah
    0.06
    pricing
    0.06
    emoji
    0.06
    Act Density 0.200%

    No Known Activations