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

    Neuronpedia

    INDEX
    Explanations

    code formatting elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    1.04
    am
    0.98
    ab
    0.96
    ud
    0.87
    ic
    0.84
    }
    0.81
     Photos
    0.80
    ew
    0.80
    ala
    0.79
    atap
    0.79
    POSITIVE LOGITS
    窕
    1.01
     congenial
    1.00
     invariable
    1.00
    Ẫ
    0.97
    ర్టు
    0.94
     Ouvrard
    0.94
    Như
    0.94
    ್ಟ
    0.93
     cancelar
    0.93
    也不能
    0.91
    Act Density 0.000%

    No Known Activations