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

    Neuronpedia

    INDEX
    Explanations

    from the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    1.01
    ла
    0.96
    ات
    0.94
     وبين
    0.92
     standpoint
    0.92
    та
    0.89
    ه
    0.89
    う
    0.89
    ে
    0.88
    它
    0.85
    POSITIVE LOGITS
     Veuillez
    0.77
    ES
    0.77
     olhando
    0.77
     elenco
    0.75
    mehr
    0.75
     együtt
    0.74
    transistors
    0.73
     intégr
    0.73
    Altri
    0.71
     veuillez
    0.71
    Act Density 0.067%

    No Known Activations