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

    Neuronpedia

    INDEX
    Explanations

    Container

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чит
    -0.07
     Positive
    -0.07
    algo
    -0.06
    AC
    -0.06
    身上
    -0.06
    results
    -0.06
    FINITE
    -0.06
    rai
    -0.06
    德
    -0.06
    ивают
    -0.06
    POSITIVE LOGITS
    gary
    0.07
     faux
    0.07
    κας
    0.06
     ἀ
    0.06
    ”
    0.06
     RECT
    0.06
    _revision
    0.06
    .gateway
    0.06
    Claim
    0.06
    坛
    0.06
    Act Density 0.004%

    No Known Activations