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

    Neuronpedia

    INDEX
    Explanations

    entertaining children

    np_max-act · gemini-2.0-flash

    The neuron fires on marketing-style, call-to-action language (e.g. ad copy, promotional appeals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     authorize
    -0.06
     Kinect
    -0.06
     sentir
    -0.06
    dispatcher
    -0.06
    	height
    -0.06
     cnt
    -0.06
    DEBUG
    -0.06
     novels
    -0.06
    328
    -0.06
     getchar
    -0.06
    POSITIVE LOGITS
    ateway
    0.07
     Dia
    0.07
    Movement
    0.06
    /&
    0.06
    rum
    0.06
    ！');↵
    0.06
    yped
    0.06
     stavu
    0.06
     оформ
    0.06
    aption
    0.06
    Act Density 0.074%

    No Known Activations