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

    Neuronpedia

    INDEX
    Explanations

    Black hole entropy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     非
    -0.07
    51
    -0.06
     CONTROL
    -0.06
    fax
    -0.06
     BEL
    -0.06
    .footer
    -0.06
    _events
    -0.06
    -E
    -0.06
    -c
    -0.06
    .Username
    -0.06
    POSITIVE LOGITS
    (animated
    0.07
    _deg
    0.06
    (figsize
    0.06
     tarn
    0.06
     outsider
    0.06
    enefit
    0.06
    λία
    0.06
    ynec
    0.06
    ografie
    0.06
    كه
    0.06
    Act Density 0.009%

    No Known Activations