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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deneyim
    -0.07
    исс
    -0.07
     ＼
    -0.06
    /favicon
    -0.06
     raison
    -0.06
     lyon
    -0.06
     dragon
    -0.06
     Madness
    -0.06
     ITS
    -0.06
     carriage
    -0.06
    POSITIVE LOGITS
    연
    0.07
    加载
    0.06
    ição
    0.06
    后的
    0.06
    athing
    0.06
     Metric
    0.06
     overst
    0.06
    土
    0.06
    _INTER
    0.06
    anga
    0.06
    Act Density 0.010%

    No Known Activations