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
     realm
    -0.08
     PRIMARY
    -0.07
     slain
    -0.07
    .argument
    -0.06
     �
    -0.06
     Bloody
    -0.06
    .ToolStrip
    -0.06
    _find
    -0.06
    Reusable
    -0.06
    .Comm
    -0.06
    POSITIVE LOGITS
    】
    0.08
    伤
    0.08
    不同
    0.06
    .**************
    0.06
     antenn
    0.06
     rever
    0.06
    Ÿ
    0.06
     franchises
    0.06
    ốn
    0.06
     inadequate
    0.06
    Act Density 0.000%

    No Known Activations