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

    Neuronpedia

    INDEX
    Explanations

    suit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ────────
    -0.08
    ogie
    -0.07
    途
    -0.07
     Spiele
    -0.07
    ას
    -0.07
    _tail
    -0.07
     housekeeping
    -0.07
    DATABASE
    -0.07
    ייך
    -0.07
    ――
    -0.07
    POSITIVE LOGITS
    ulario
    0.09
     стане
    0.07
     Австра
    0.07
    lude
    0.07
     bunker
    0.07
    frig
    0.07
    евер
    0.07
     смерти
    0.07
    .eval
    0.07
    Pods
    0.07
    Act Density 0.006%

    No Known Activations