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

    Neuronpedia

    INDEX
    Explanations

    code/technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <H
    -0.08
    莱
    -0.06
    أم
    -0.06
    Clr
    -0.06
    “So
    -0.06
    FB
    -0.06
    LECT
    -0.06
     �
    -0.06
    �
    -0.06
    YPD
    -0.06
    POSITIVE LOGITS
     ск
    0.07
     fixing
    0.07
    esehen
    0.06
     rej
    0.06
     şiş
    0.06
    Elim
    0.06
    .advance
    0.06
    uhl
    0.06
    _Msk
    0.06
     });↵↵
    0.06
    Act Density 0.000%

    No Known Activations