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

    Neuronpedia

    INDEX
    Explanations

    dates especially 1990s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _checkbox
    -0.07
    HEL
    -0.07
     top
    -0.07
    Verts
    -0.07
     Jong
    -0.07
     nový
    -0.07
    Tony
    -0.07
     Suche
    -0.07
     chained
    -0.06
     ///
    -0.06
    POSITIVE LOGITS
    _iters
    0.07
     �
    0.07
     edilmiştir
    0.07
     Peygamber
    0.06
    اعت
    0.06
    历
    0.06
     채
    0.06
     frequ
    0.06
     державної
    0.06
    Receipt
    0.06
    Act Density 0.036%

    No Known Activations