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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the second‐person pronoun (“you”)—especially in constructions that frame rhetorical or admonishing questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ToolTip
    -0.07
    Integral
    -0.07
     entrance
    -0.07
     项
    -0.06
    roups
    -0.06
    	align
    -0.06
    })↵↵
    -0.06
     signifies
    -0.06
    Modal
    -0.06
     terrific
    -0.06
    POSITIVE LOGITS
     adını
    0.06
     soukrom
    0.06
    .ipv
    0.06
    leet
    0.06
    ิม
    0.06
     çı
    0.06
    _adv
    0.06
     Kaf
    0.06
    _favorite
    0.06
    orca
    0.06
    Act Density 0.040%

    No Known Activations