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

    Neuronpedia

    INDEX
    Explanations

    talking

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that signal a discussion or conversational exchange between characters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     toile
    -0.07
     Opcode
    -0.06
     Speech
    -0.06
    ách
    -0.06
     creature
    -0.06
    District
    -0.06
     شیر
    -0.06
     Sc
    -0.06
    ahoma
    -0.06
     Tk
    -0.06
    POSITIVE LOGITS
    uddy
    0.07
    .bl
    0.07
     Ky
    0.06
    _FOR
    0.06
    บาล
    0.06
     groupe
    0.06
     pageSize
    0.06
    ●●●●●●●●●●●●●●●●
    0.06
    entreprise
    0.06
    	fi
    0.06
    Act Density 0.015%

    No Known Activations