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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash

    The neuron fires on the phrase “don’t need to” (and close variants), i.e. expressions indicating that something is not necessary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hoff
    -0.08
     Pregn
    -0.07
     loggedIn
    -0.07
    _PANEL
    -0.07
     �
    -0.07
     safeg
    -0.07
    avn
    -0.07
     προς
    -0.07
    Truthy
    -0.07
    μβρίου
    -0.06
    POSITIVE LOGITS
     needing
    0.07
    0.06
    alogy
    0.06
    0.05
    /token
    0.05
    0.05
    0.05
    0.05
    <'
    0.05
     {:?}",
    0.05
    Act Density 0.018%

    No Known Activations