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

    Neuronpedia

    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leased
    -0.07
    ologically
    -0.06
    タル
    -0.06
    ulary
    -0.06
    єю
    -0.06
    Scotland
    -0.06
    olic
    -0.06
     фрон
    -0.06
    -cent
    -0.06
     caster
    -0.06
    POSITIVE LOGITS
     keeps
    0.08
     kept
    0.07
     keep
    0.06
     Handy
    0.06
     Drain
    0.06
    ););↵
    0.06
     whole
    0.06
    _lookup
    0.06
    Monitor
    0.06
     recv
    0.06
    Act Density 0.013%

    No Known Activations