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

    Neuronpedia

    INDEX
    Explanations

    medal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "F
    -0.07
     کوچ
    -0.07
     origins
    -0.07
     ersten
    -0.06
    *)&
    -0.06
     CType
    -0.06
    "%(
    -0.06
    Orientation
    -0.06
    .pipe
    -0.06
    Firefox
    -0.06
    POSITIVE LOGITS
    ้าต
    0.06
     وغير
    0.06
     λέ
    0.06
     Downtown
    0.06
     nguyên
    0.06
     sidewalks
    0.06
     �
    0.06
     kola
    0.06
     mezi
    0.06
    िलत
    0.06
    Act Density 0.001%

    No Known Activations