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

    Neuronpedia

    INDEX
    Explanations

    Group

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瘃
    -0.08
    Whole
    -0.07
    ڗ
    -0.07
    which
    -0.07
    otation
    -0.07
    휑
    -0.07
    贩
    -0.07
    🌕
    -0.06
     Matte
    -0.06
     [];
    -0.06
    POSITIVE LOGITS
    _PAD
    0.07
    .masks
    0.07
     whiskey
    0.07
     Manager
    0.07
     qb
    0.07
    न
    0.07
     resilience
    0.07
    IG
    0.07
     Army
    0.07
     Wilmington
    0.06
    Act Density 0.001%

    No Known Activations