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

    Neuronpedia

    INDEX
    Explanations

    game engines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ятия
    -0.06
    382
    -0.06
    fil
    -0.06
    .Screen
    -0.06
    239
    -0.06
    アルバ
    -0.06
    ()):↵
    -0.06
     BRE
    -0.06
    rovers
    -0.06
     safeguard
    -0.06
    POSITIVE LOGITS
     rok
    0.07
     unmarried
    0.06
    .netbeans
    0.06
     posing
    0.06
     Поч
    0.06
    _Click
    0.06
       
    0.06
    ('__
    0.06
     sadd
    0.06
    щ
    0.06
    Act Density 0.025%

    No Known Activations