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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yurt
    -0.07
     yer
    -0.07
    cern
    -0.07
    bots
    -0.07
     Primer
    -0.06
    cad
    -0.06
    _hid
    -0.06
    filepath
    -0.06
     sos
    -0.06
    ━━━━━━━━
    -0.06
    POSITIVE LOGITS
    '}}>↵
    0.07
     _("
    0.06
    =======↵
    0.06
    '})↵
    0.06
    éf
    0.06
     νεφ
    0.06
    =_("
    0.06
    =_('
    0.06
    ']}↵
    0.06
     филь
    0.06
    Act Density 0.014%

    No Known Activations