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

    Neuronpedia

    INDEX
    Explanations

    emotions

    np_max-act · gemini-2.0-flash

    This neuron responds to words and phrases about exploring or guiding characters’ emotions, thoughts, and interactions—that is, meta-narrative or roleplay instruction language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eyin
    -0.07
     Hoa
    -0.07
     '['
    -0.07
     Huang
    -0.06
     TMP
    -0.06
    (attr
    -0.06
     SWT
    -0.06
     GS
    -0.06
     že
    -0.06
     Abraham
    -0.06
    POSITIVE LOGITS
     intellectuals
    0.08
    ुह
    0.07
     SUCCESS
    0.07
    握
    0.06
    ocomplete
    0.06
     Navigate
    0.06
     buộc
    0.06
    phans
    0.06
     plotting
    0.06
    inks
    0.06
    Act Density 0.005%

    No Known Activations