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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     каль
    -0.06
     Nah
    -0.06
     needing
    -0.06
    -init
    -0.06
    requested
    -0.05
    _a
    -0.05
     subdir
    -0.05
    Sharper
    -0.05
     wur
    -0.05
     rá
    -0.05
    POSITIVE LOGITS
    .transfer
    0.08
    angered
    0.07
    onds
    0.07
    cum
    0.07
     completion
    0.07
    幼
    0.07
    IALIZED
    0.07
    ザー
    0.07
    _death
    0.06
     unfairly
    0.06
    Act Density 0.000%

    No Known Activations