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

    Neuronpedia

    INDEX
    Explanations

    />

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”
    -0.08
     Centers
    -0.07
    ne
    -0.06
     care
    -0.06
     be
    -0.06
     Q
    -0.06
     mse
    -0.06
    样
    -0.06
    è
    -0.06
    =e
    -0.06
    POSITIVE LOGITS
    .hwp
    0.07
    .if
    0.07
    ίκη
    0.07
    .backgroundColor
    0.07
    .Hand
    0.07
     �
    0.07
    DIST
    0.07
    _URL
    0.06
    lijah
    0.06
    Demon
    0.06
    Act Density 0.012%

    No Known Activations