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

    Neuronpedia

    INDEX
    Explanations

    the word "everything" and related words such as "anything," as well as some preceding context

    oai_token-act-pair · gemini-2.0-flash

    everything/anything

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мәкал
    -0.57
     Dinge
    -0.52
     Everything
    -0.51
    delig
    -0.50
     forti
    -0.50
     vieles
    -0.49
     Things
    -0.49
    Everything
    -0.49
    Становништво
    -0.48
    everything
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.73
    DockStyle
    0.61
    DeleteBehavior
    0.61
    SupportActionBar
    0.60
     beginnetje
    0.59
    saraba
    0.59
    yntaxException
    0.57
     autorytatywna
    0.57
    exitRule
    0.57
    ReusableCell
    0.56
    Act Density 3.401%

    No Known Activations