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

    Neuronpedia

    INDEX
    Explanations

    etymonline links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mailbox
    0.42
    achsen
    0.37
     சோ
    0.36
    }]\
    0.36
    liceerd
    0.36
    ambia
    0.36
     schen
    0.36
     flagpole
    0.35
     XB
    0.35
    钤
    0.35
    POSITIVE LOGITS
     Converts
    0.42
    š
    0.40
     converts
    0.38
     Convert
    0.38
    typename
    0.38
     Auto
    0.38
    目の
    0.37
    ͠
    0.37
    idus
    0.36
     老
    0.36
    Act Density 0.001%

    No Known Activations