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

    Neuronpedia

    INDEX
    Explanations

    biological/born

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sloppy
    -0.08
    ße
    -0.07
    dash
    -0.07
    筢
    -0.07
    styled
    -0.07
    -Bold
    -0.07
    �
    -0.07
    כנות
    -0.07
    ]];↵
    -0.07
    hoc
    -0.07
    POSITIVE LOGITS
    主角
    0.08
    .toString
    0.07
    (compact
    0.07
     요구
    0.07
    .invalid
    0.07
     gốc
    0.07
     ثنائي
    0.07
    なのか
    0.07
    /%
    0.07
    存活
    0.07
    Act Density 0.028%

    No Known Activations