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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    σσ
    -0.06
    -light
    -0.06
    стров
    -0.06
    شاء
    -0.06
    utf
    -0.06
     aggressive
    -0.06
    ts
    -0.06
    rms
    -0.06
     //.
    -0.06
    POSITIVE LOGITS
    oti
    0.07
     NAT
    0.07
    (dm
    0.07
     BMC
    0.06
     Cheese
    0.06
    cplusplus
    0.06
    _TIMER
    0.06
    (Op
    0.06
    rgyz
    0.06
     Hip
    0.06
    Act Density 0.000%

    No Known Activations