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

    Neuronpedia

    INDEX
    Explanations

    challenges/problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assoluto
    -0.65
    chiali
    -0.65
    PreferredItem
    -0.64
     messaggi
    -0.64
    DockStyle
    -0.63
     configureStore
    -0.63
    IInterface
    -0.62
    olak
    -0.62
    SharedCtor
    -0.62
    MemoryWarning
    -0.61
    POSITIVE LOGITS
     time
    0.57
    time
    0.43
     and
    0.41
    URLEncoder
    0.40
     eme
    0.38
    zedł
    0.38
     emergency
    0.37
    惘
    0.37
    nonatomic
    0.36
    OptionsMenu
    0.36
    Act Density 0.006%

    No Known Activations