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

    Neuronpedia

    INDEX
    Explanations

    public,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ージー
    0.38
    Ｙ
    0.37
    ంత్ర
    0.36
     छठी
    0.36
     ViewHolder
    0.36
    지와
    0.35
     एमएन
    0.35
    வழி
    0.35
     floss
    0.35
    Cellphone
    0.34
    POSITIVE LOGITS
     Tu
    0.40
    Tu
    0.38
     Franck
    0.38
    ᱫ
    0.37
    ٹین
    0.36
    Principles
    0.36
    नीर
    0.35
    cond
    0.34
    hors
    0.34
     Dick
    0.34
    Act Density 0.008%

    No Known Activations