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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the second-person pronoun “you,” especially in polite user requests (e.g. “Can you…?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     publication
    -0.07
     MMP
    -0.06
     isl
    -0.06
    Pager
    -0.06
     dishes
    -0.06
    _lifetime
    -0.06
    	first
    -0.06
     illnesses
    -0.06
    ło
    -0.06
    Template
    -0.06
    POSITIVE LOGITS
     secs
    0.06
     getSource
    0.06
     состоянии
    0.06
     Leia
    0.06
    _der
    0.06
    eding
    0.06
    (dep
    0.06
     وصلات
    0.06
     majors
    0.06
    уванні
    0.06
    Act Density 0.020%

    No Known Activations