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

    Neuronpedia

    INDEX
    Explanations

    resources for support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assessments
    0.74
    ijske
    0.74
     DRN
    0.73
    ijn
    0.73
     determinations
    0.73
    énagement
    0.72
     objectives
    0.71
    uties
    0.71
    UMENT
    0.70
    ENING
    0.70
    POSITIVE LOGITS
     मुस्
    0.57
     做
    0.56
    Powered
    0.56
     limpiar
    0.56
     as
    0.56
     Mah
    0.55
     related
    0.54
    Enc
    0.54
     relacionado
    0.53
     Encode
    0.53
    Act Density 0.417%

    No Known Activations