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

    Neuronpedia

    INDEX
    Explanations

    references to the existence or availability of information or data

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

    absence of something exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.52
     GenerationType
    -0.39
    errHandler
    -0.38
    +:+
    -0.37
     thận
    -0.36
    一件
    -0.34
    OGND
    -0.34
    disfraz
    -0.32
     переписи
    -0.32
     nữa
    -0.31
    POSITIVE LOGITS
     none
    0.73
    nothing
    0.69
    none
    0.68
     nothing
    0.66
    Nothing
    0.66
     nessuna
    0.65
     NOTHING
    0.64
     nowhere
    0.63
     Nothing
    0.63
     الحره
    0.63
    Act Density 0.111%

    No Known Activations