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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various methods and tips

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

    book signing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.47
    __(/*!
    -0.40
    IBOutlet
    -0.40
    omock
    -0.39
    MENAFN
    -0.37
     bounce
    -0.36
    ArgsConstructor
    -0.36
    ValueStyle
    -0.34
    новништво
    -0.34
    CloseOperation
    -0.34
    POSITIVE LOGITS
    iglio
    0.49
    новниш
    0.49
     IFTT
    0.44
    SharedCtor
    0.44
    ništ
    0.44
     فريبيس
    0.42
    dflare
    0.42
    afone
    0.42
    psack
    0.42
    Datuak
    0.42
    Act Density 0.079%

    No Known Activations