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

    Neuronpedia

    INDEX
    Explanations

    biological and technical processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ástico
    0.39
    acic
    0.37
    raron
    0.37
     mês
    0.37
     Gir
    0.36
    атр
    0.36
    preceq
    0.35
    സിന്റെ
    0.35
    endido
    0.35
    lasti
    0.35
    POSITIVE LOGITS
    کتر
    0.41
    죽
    0.38
    モデル
    0.38
     polishing
    0.37
     orientación
    0.37
     rupam
    0.36
    ANTES
    0.36
    テ
    0.36
     puriso
    0.36
    Scr
    0.36
    Act Density 0.000%

    No Known Activations