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

    Neuronpedia

    INDEX
    Explanations

    transl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dx
    -0.07
    ]),↵
    -0.06
     Self
    -0.06
     Copper
    -0.06
    culated
    -0.06
    าจะ
    -0.06
     impe
    -0.06
     pais
    -0.05
     попада
    -0.05
     Dashboard
    -0.05
    POSITIVE LOGITS
    ext
    0.08
    /<
    0.07
    ümü
    0.07
    NODE
    0.07
    ็นท
    0.06
    _SOFT
    0.06
    madan
    0.06
    SUB
    0.06
      
    0.06
    自动
    0.06
    Act Density 0.000%

    No Known Activations