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

    Neuronpedia

    INDEX
    Explanations

    code data responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     ниже
    -0.06
     안전
    -0.06
     Wrong
    -0.06
    なくな
    -0.06
    ालय
    -0.06
    提交
    -0.06
    221
    -0.06
    ый
    -0.06
    ателей
    -0.06
    POSITIVE LOGITS
    _SHIFT
    0.07
    asha
    0.07
    .ACT
    0.07
    APON
    0.07
    MIN
    0.06
    (Packet
    0.06
    apon
    0.06
    #{
    0.06
    (per
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations