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

    Neuronpedia

    INDEX
    Explanations

    ggerganov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jes
    0.69
    فة
    0.69
    jež
    0.67
     piv
    0.64
     vivido
    0.63
    оте
    0.63
    كي
    0.62
    楽しい
    0.62
     snub
    0.62
    ුවේ
    0.62
    POSITIVE LOGITS
    ई
    0.84
     সঙ্গ
    0.67
    ോള
    0.63
     л
    0.63
     நே
    0.62
    eaa
    0.62
    umb
    0.62
     ல
    0.61
     изд
    0.61
     régi
    0.60
    Act Density 0.001%

    No Known Activations