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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Usuario
    -0.07
    Hel
    -0.07
     клад
    -0.06
     kterých
    -0.06
     Performs
    -0.06
    _UTIL
    -0.06
    هد
    -0.06
     læ
    -0.06
    _lvl
    -0.06
    Adam
    -0.06
    POSITIVE LOGITS
     '">
    0.07
     recept
    0.07
    *);↵
    0.07
    *))
    0.06
    metric
    0.06
    派
    0.06
    '</
    0.06
     erad
    0.06
    ISMATCH
    0.06
    YK
    0.06
    Act Density 0.001%

    No Known Activations