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

    Neuronpedia

    INDEX
    Explanations

    changes and inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greed
    0.51
    ادیه
    0.49
     Hindu
    0.47
     hindu
    0.47
     moteur
    0.47
     unica
    0.46
     k
    0.45
     pode
    0.45
     Preis
    0.44
     zeal
    0.44
    POSITIVE LOGITS
     школова
    0.53
    nearly
    0.46
    faced
    0.45
    Nearly
    0.42
    lesssim
    0.42
    ெல்லாம்
    0.41
    discuss
    0.41
    augmented
    0.41
    Vac
    0.40
     buildFor
    0.40
    Act Density 0.005%

    No Known Activations