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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminologies and concepts related to functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    arbitrary and local expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectMocks
    -0.65
    IBOutlet
    -0.63
    MemoryWarning
    -0.57
     كومونز
    -0.57
    ollectionView
    -0.56
     <<<<<<<<<<<<<<
    -0.53
    Kanpo
    -0.52
     IBOutlet
    -0.52
    ⤹
    -0.49
     للمعارف
    -0.49
    POSITIVE LOGITS
    Rujuakan
    0.42
     získ
    0.38
    writeField
    0.36
     attiva
    0.35
     inderdaad
    0.35
     sledo
    0.33
     hack
    0.33
     vů
    0.33
     culoare
    0.33
    plaat
    0.32
    Act Density 0.297%

    No Known Activations