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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    phrases that express permission, ability, or the availability of a feature (words like "allow(s)", "ability", "allowing", etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ipated
    -0.07
    VM
    -0.07
    cura
    -0.07
    ()][
    -0.06
    ář
    -0.06
    angkan
    -0.06
    يار
    -0.06
    ppe
    -0.06
     Hib
    -0.06
    щий
    -0.06
    POSITIVE LOGITS
    _aut
    0.07
     folk
    0.07
    .bootstrapcdn
    0.07
    .CONNECT
    0.06
     Nonetheless
    0.06
    Directive
    0.06
     Ссылки
    0.06
     emlrt
    0.06
    Meanwhile
    0.06
    _CALL
    0.06
    Act Density 0.374%

    No Known Activations