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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash

    This neuron activates on words signaling recent developments or ongoing innovation (e.g., “new,” “being,” “developed,” “introduced,” “evolving”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	resolve
    -0.06
    夫
    -0.06
     Fot
    -0.06
     υπηρε
    -0.06
     attack
    -0.06
    　
    -0.06
     Operand
    -0.06
    	post
    -0.06
     Mash
    -0.06
    mime
    -0.06
    POSITIVE LOGITS
    908
    0.07
    _AL
    0.07
    _MO
    0.07
    .NEW
    0.07
    ZONE
    0.06
    ğü
    0.06
     PU
    0.06
    aroo
    0.06
    _MODEL
    0.06
    ổi
    0.06
    Act Density 0.035%

    No Known Activations