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

    Neuronpedia

    INDEX
    Explanations

    . Where. The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banter
    0.82
     mutlaka
    0.78
     eclectic
    0.78
     zakup
    0.78
     acheté
    0.78
     putea
    0.78
    致力
    0.78
     flamboyant
    0.77
     músicos
    0.77
     জবাব
    0.77
    POSITIVE LOGITS
     Notice
    1.45
     Note
    1.41
    Notice
    1.39
    Note
    1.35
     note
    1.34
     notice
    1.34
     Since
    1.27
    Since
    1.22
    note
    1.13
     Because
    1.09
    Act Density 2.085%

    No Known Activations