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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explained
    -0.06
    _Connection
    -0.06
     waiting
    -0.06
    ’am
    -0.06
     только
    -0.06
     battling
    -0.06
     confined
    -0.06
     regarded
    -0.06
    се
    -0.06
    ै
    -0.06
    POSITIVE LOGITS
     ovar
    0.07
    权限
    0.07
    essoa
    0.06
    .ro
    0.06
    üne
    0.06
    _pix
    0.06
    .sale
    0.06
    _cmp
    0.06
     bmp
    0.06
     Goddess
    0.06
    Act Density 0.218%

    No Known Activations