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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    part
    -0.07
    /fire
    -0.07
    handles
    -0.07
    strain
    -0.06
    partition
    -0.06
     Knowledge
    -0.06
    REQUEST
    -0.06
     intervening
    -0.06
    очь
    -0.06
     아직
    -0.06
    POSITIVE LOGITS
     Ips
    0.06
    _ABI
    0.06
     demi
    0.06
     imm
    0.06
    .onResume
    0.06
    (sig
    0.06
    φό
    0.06
    .tcp
    0.06
     dön
    0.06
     enums
    0.06
    Act Density 0.017%

    No Known Activations