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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Press
    -0.07
    Wil
    -0.07
     Psych
    -0.07
     psych
    -0.07
    .setLevel
    -0.06
    utschein
    -0.06
    physical
    -0.06
    189
    -0.06
    potential
    -0.06
    .Unsupported
    -0.06
    POSITIVE LOGITS
    �
    0.08
     interruption
    0.08
    (SK
    0.07
     거
    0.07
    ाच
    0.07
     Ά
    0.07
     Stone
    0.07
    .xx
    0.07
     креп
    0.07
     Гар
    0.06
    Act Density 0.014%

    No Known Activations