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
     blot
    -0.07
    д
    -0.07
    033
    -0.07
    414
    -0.06
     colour
    -0.06
    053
    -0.06
    ICIAL
    -0.06
    ولوج
    -0.06
     //↵↵
    -0.06
    morph
    -0.06
    POSITIVE LOGITS
    そ
    0.07
    _SCL
    0.06
     dikkat
    0.06
    (freq
    0.06
     тис
    0.06
    Verb
    0.06
     KING
    0.06
     Shelley
    0.06
    _ml
    0.06
    两人
    0.06
    Act Density 0.183%

    No Known Activations