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

    Neuronpedia

    INDEX
    Explanations

    public function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Πολ
    0.48
     Professionals
    0.46
    】.
    0.46
     Wilkes
    0.46
    cześ
    0.45
     Apartments
    0.44
     సంబంధ
    0.44
    formerly
    0.43
     Großbritannien
    0.43
     organiques
    0.43
    POSITIVE LOGITS
    ד
    0.51
    게
    0.49
     to
    0.45
     pog
    0.45
     به
    0.44
     itu
    0.44
     chameleon
    0.44
    ע
    0.43
    opic
    0.43
     singkat
    0.42
    Act Density 0.007%

    No Known Activations