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

    Neuronpedia

    INDEX
    Explanations

    you linked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MovieModal
    0.91
     serviço
    0.83
     thermocou
    0.83
    '];
    0.82
    stances
    0.81
    Gaussian
    0.80
    အတူ
    0.79
     participação
    0.79
    FromArgb
    0.79
    uterine
    0.77
    POSITIVE LOGITS
    te
    0.70
    ndash
    0.67
     Allora
    0.67
    ى
    0.67
    ll
    0.66
     Jillian
    0.64
    بال
    0.63
    ر
    0.63
    here
    0.63
    bian
    0.62
    Act Density 0.001%

    No Known Activations