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

    Neuronpedia

    INDEX
    Explanations

    fashion and style

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하는
    -0.07
     sellers
    -0.07
    <typeof
    -0.07
    なる
    -0.07
     commute
    -0.06
    (DBG
    -0.06
    =-
    -0.06
    她
    -0.06
    Contract
    -0.06
     slit
    -0.06
    POSITIVE LOGITS
    �
    0.06
     인구
    0.06
    ١
    0.06
    __;
    0.06
    /NĐ
    0.06
     monde
    0.06
     �
    0.06
    ibi
    0.06
    stial
    0.06
     _('
    0.06
    Act Density 0.025%

    No Known Activations