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

    Neuronpedia

    INDEX
    Explanations

    say "number 2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Purchase
    -0.07
    �
    -0.07
    ┳
    -0.07
    .Must
    -0.07
     Locations
    -0.07
    .getC
    -0.06
    vinces
    -0.06
    Crypt
    -0.06
     Snapshot
    -0.06
     Throughout
    -0.06
    POSITIVE LOGITS
    让他
    0.08
    安倍
    0.07
     irritating
    0.07
     котором
    0.07
    amping
    0.07
    datable
    0.07
    榰
    0.07
    核查
    0.06
    让消费者
    0.06
    ลาน
    0.06
    Act Density 0.022%

    No Known Activations