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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rask
    -0.56
     Paro
    -0.55
     Organisation
    -0.52
     organized
    -0.49
    guli
    -0.49
    leine
    -0.48
    日閲覧
    -0.48
    Ử
    -0.48
     Organization
    -0.48
    udin
    -0.47
    POSITIVE LOGITS
     صوتيه
    0.76
    WebVitals
    0.72
    MemoryWarning
    0.69
     виправивши
    0.61
    destroyAll
    0.60
    abetes
    0.58
    futbolista
    0.57
    ConstraintMaker
    0.56
    tableFuture
    0.56
    rungsseite
    0.54
    Act Density 0.021%

    No Known Activations