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

    Neuronpedia

    INDEX
    Explanations

    traditional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    厚厚的
    -0.07
    attle
    -0.07
     Permit
    -0.07
    OLID
    -0.07
    ᠢ
    -0.07
     insist
    -0.07
    _cov
    -0.06
    ycle
    -0.06
    せて
    -0.06
    EL
    -0.06
    POSITIVE LOGITS
    Earn
    0.08
    _segments
    0.08
     kn
    0.07
     scr
    0.07
    _supported
    0.07
    _external
    0.07
    _pressed
    0.06
     Como
    0.06
     �
    0.06
    诣
    0.06
    Act Density 0.038%

    No Known Activations