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

    Neuronpedia

    INDEX
    Explanations

    manipulate

    np_max-act · gemini-2.0-flash

    The neuron peaks on words and stems related to manipulation or persuasive influence (e.g. “manipulate,” “manipulation,” “propaganda”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    夏
    -0.07
     Tea
    -0.06
     outset
    -0.06
    luck
    -0.06
    _clock
    -0.06
     Oprah
    -0.06
    Datetime
    -0.06
     sol
    -0.06
     источ
    -0.06
    itespace
    -0.06
    POSITIVE LOGITS
     Methods
    0.06
     CGI
    0.06
     infiltr
    0.06
     reserve
    0.06
    PageSize
    0.06
    ((&
    0.06
    _between
    0.06
     Fuller
    0.06
    mpeg
    0.06
     여자
    0.06
    Act Density 0.014%

    No Known Activations