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

    Neuronpedia

    INDEX
    Explanations

    Loveisrespect resource links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    班牙
    1.76
     Duties
    1.69
    湡
    1.68
    ࿐
    1.66
     Decomposition
    1.66
     speedily
    1.61
     ASME
    1.61
     Muscles
    1.60
     Ayurvedic
    1.58
     solubilities
    1.57
    POSITIVE LOGITS
    ième
    1.88
    n
    1.74
    ю
    1.70
     começa
    1.69
    nivel
    1.65
     क्रमांका
    1.65
    inch
    1.61
    m
    1.58
     Disse
    1.57
    на
    1.53
    Act Density 0.000%

    No Known Activations