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

    Neuronpedia

    INDEX
    Explanations

    block card or password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Та
    1.25
    Экс
    1.14
     придется
    1.09
    Го
    1.08
    容
    1.03
     چلا
    0.99
    Retour
    0.97
    大约
    0.96
    ب
    0.95
    ুর
    0.94
    POSITIVE LOGITS
    ्यूट
    1.23
    isVisible
    1.20
    д
    1.17
     stata
    1.16
     Garuda
    1.15
    hearted
    1.15
    promised
    1.15
     नती
    1.14
     HCV
    1.13
     Vessel
    1.13
    Act Density 0.000%

    No Known Activations