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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、「
    -0.06
     analiz
    -0.06
    にある
    -0.06
     bf
    -0.06
     хотя
    -0.06
     arrests
    -0.06
    -builder
    -0.06
    中的
    -0.06
     solver
    -0.06
     relations
    -0.06
    POSITIVE LOGITS
    HEEL
    0.07
    0.07
     Chanel
    0.07
    展
    0.07
    rát
    0.07
     revel
    0.07
    (changes
    0.06
    ději
    0.06
    [prop
    0.06
    ová
    0.06
    Act Density 0.000%

    No Known Activations