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

    Neuronpedia

    INDEX
    Explanations

    mechanisms/mechanization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EndContext
    -0.67
    ftagPool
    -0.63
    (!__
    -0.63
     privée
    -0.62
    KURZBESCHREIBUNG
    -0.62
     المعيارى
    -0.59
     privé
    -0.57
    styleType
    -0.57
     disponibilités
    -0.57
     Lath
    -0.56
    POSITIVE LOGITS
    posites
    0.55
    archiviato
    0.54
    KeySpec
    0.52
     unknownFields
    0.51
     IMDB
    0.50
    awaiter
    0.49
     Region
    0.49
     UnityEngine
    0.47
    זיה
    0.47
     Sal
    0.45
    Act Density 0.079%

    No Known Activations