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

    Neuronpedia

    INDEX
    Explanations

    trained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैग
    -0.07
    ripsi
    -0.07
    Encrypt
    -0.06
     oy
    -0.06
    iệ
    -0.06
     EXAMPLE
    -0.06
    άλ
    -0.06
     developers
    -0.06
    piler
    -0.06
     bisexual
    -0.06
    POSITIVE LOGITS
     commit
    0.07
     Cartesian
    0.07
     maxlen
    0.07
    ธน
    0.06
     Bou
    0.06
    _ERR
    0.06
    [parent
    0.06
     récup
    0.06
    默认
    0.06
     φω
    0.06
    Act Density 0.001%

    No Known Activations