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

    Neuronpedia

    INDEX
    Explanations

    waiting for something

    np_max-act · gemini-2.0-flash

    This neuron detects marketing pitch phrases that directly address the reader with “you’ve been … for” or “you’ve always wanted” constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ("""
    -0.07
     headaches
    -0.06
    他の
    -0.06
    ``
    -0.06
     massac
    -0.06
    ingle
    -0.06
     справи
    -0.06
    -makers
    -0.06
    .goBack
    -0.06
    ()))
↵
    -0.06
    POSITIVE LOGITS
     lối
    0.07
    �
    0.07
    San
    0.07
    	Created
    0.06
    raw
    0.06
     {{$
    0.06
     tried
    0.06
    .getLabel
    0.06
    科
    0.06
    .sc
    0.06
    Act Density 0.018%

    No Known Activations