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
    ่ะ
    -0.07
     cualquier
    -0.06
    -0.06
    .Parameter
    -0.06
     Curse
    -0.06
    Altern
    -0.06
    .En
    -0.06
    atha
    -0.06
     ún
    -0.06
    /comment
    -0.06
    POSITIVE LOGITS
    ?option
    0.06
     свої
    0.06
    城
    0.06
    �
    0.06
     bitmask
    0.06
    ieder
    0.06
     vận
    0.06
     pub
    0.05
     fires
    0.05
    Defined
    0.05
    Act Density 0.062%

    No Known Activations