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

    Neuronpedia

    INDEX
    Explanations

    list items or structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Io
    0.47
    কার্য
    0.47
    roe
    0.45
    Ice
    0.45
    Title
    0.45
    Ia
    0.45
    ".
    0.44
    க்கு
    0.43
     повре
    0.43
    Ic
    0.43
    POSITIVE LOGITS
     landen
    0.46
     jobSearch
    0.46
     e
    0.45
     diversité
    0.44
     письмо
    0.44
     Є
    0.44
     kinderen
    0.43
     लाभार्थियों
    0.43
     ఫ్రె
    0.43
     discuss
    0.43
    Act Density 0.001%

    No Known Activations