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

    Neuronpedia

    INDEX
    Explanations

    project management implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کان
    0.38
    res
    0.37
    し
    0.37
    کس
    0.36
     پی
    0.36
    าร
    0.34
    は
    0.34
    risy
    0.33
     دی
    0.33
     که
    0.32
    POSITIVE LOGITS
    H
    0.42
    F
    0.41
    id
    0.39
     Exception
    0.37
     Bur
    0.37
    c
    0.36
     Fe
    0.36
     Lemma
    0.34
     Burgers
    0.34
    ak
    0.34
    Act Density 0.000%

    No Known Activations