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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    290
    -0.07
    .getLog
    -0.07
     tok
    -0.06
     getPage
    -0.06
    ,dim
    -0.06
     оз
    -0.06
     文
    -0.06
    arious
    -0.06
    ACIÓN
    -0.06
    ापस
    -0.06
    POSITIVE LOGITS
     only
    0.09
     solely
    0.09
    Only
    0.07
     forfeiture
    0.07
     frozen
    0.07
    style
    0.07
    .methods
    0.07
     eben
    0.06
     Sinclair
    0.06
    ONLY
    0.06
    Act Density 0.012%

    No Known Activations