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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash

    This neuron responds to negation or contrast words (e.g. “not,” “but,” “however”) signaling a change or reversal in the discourse.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	damage
    -0.08
     baj
    -0.07
     fabs
    -0.07
    :len
    -0.07
     NSS
    -0.06
     Mitch
    -0.06
    _MOBILE
    -0.06
    info
    -0.06
    SpaceItem
    -0.06
     intuition
    -0.06
    POSITIVE LOGITS
     according
    0.06
    [g
    0.06
     relação
    0.06
    _THEME
    0.06
    olution
    0.06
     sulph
    0.06
    름
    0.06
    ีว
    0.06
    _frm
    0.06
    dif
    0.06
    Act Density 0.059%

    No Known Activations