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

    Neuronpedia

    INDEX
    Explanations

    find, need, or see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einzige
    1.47
    й
    1.44
    se
    1.23
    ك
    1.19
    ிய
    1.16
    ],\
    1.16
     ausgew
    1.15
    ος
    1.11
    ιο
    1.10
    り
    1.08
    POSITIVE LOGITS
    需
    1.23
     Need
    1.17
     anci
    1.17
    ષ્ઠ
    1.16
    ć
    1.16
    可以
    1.11
    Find
    1.10
     canes
    1.10
     Find
    1.09
    experience
    1.09
    Act Density 0.049%

    No Known Activations