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

    Neuronpedia

    INDEX
    Explanations

    program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    priority
    -0.07
     QIcon
    -0.07
     RuntimeObject
    -0.06
     occurrence
    -0.06
     morality
    -0.06
    模型
    -0.06
    idade
    -0.06
    .snapshot
    -0.06
     rost
    -0.06
     глиб
    -0.06
    POSITIVE LOGITS
     accordion
    0.07
    shops
    0.07
    _APP
    0.06
     mềm
    0.06
     Shotgun
    0.06
     bloody
    0.06
    _PAR
    0.06
    ifax
    0.06
    อาหาร
    0.06
    監
    0.06
    Act Density 0.312%

    No Known Activations