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

    Neuronpedia

    INDEX
    Explanations

    promise

    np_max-act · gemini-2.0-flash

    The neuron activates on words expressing a promise or commitment (e.g. “promise”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Frog
    -0.07
     мала
    -0.06
     intend
    -0.06
     blanket
    -0.06
    Titulo
    -0.06
     nut
    -0.06
     supper
    -0.06
     juices
    -0.06
    .priority
    -0.06
    _unit
    -0.06
    POSITIVE LOGITS
    ycled
    0.07
    py
    0.07
     /**
↵
    0.07
     ${({
    0.06
    odia
    0.06
    ổng
    0.06
    onestly
    0.06
    !important
    0.06
     magical
    0.06
    än
    0.06
    Act Density 0.009%

    No Known Activations