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

    Neuronpedia

    INDEX
    Explanations

    logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blows
    -0.07
    ढ
    -0.07
    queen
    -0.07
    their
    -0.07
    _links
    -0.07
    ři
    -0.07
     their
    -0.06
    .metro
    -0.06
     derin
    -0.06
     onc
    -0.06
    POSITIVE LOGITS
    тож
    0.06
     weap
    0.06
     unterschied
    0.06
    ,,,,,,,,
    0.06
    noc
    0.06
    ERICAN
    0.06
    Sender
    0.05
     whereby
    0.05
    ئيس
    0.05
     ammon
    0.05
    Act Density 0.009%

    No Known Activations