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

    Neuronpedia

    INDEX
    Explanations

    characteristic

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the adjective “characteristic.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     directly
    -0.07
    �
    -0.06
     upper
    -0.06
    :↵↵↵↵
    -0.06
    έας
    -0.06
    NL
    -0.06
    鉄
    -0.06
     neler
    -0.06
     tremendously
    -0.06
     duplicates
    -0.06
    POSITIVE LOGITS
     distinctive
    0.11
     trademark
    0.10
     characteristic
    0.08
     hallmark
    0.07
     ASF
    0.07
     लक
    0.07
     autobi
    0.06
     gracious
    0.06
    افة
    0.06
     charismatic
    0.06
    Act Density 0.015%

    No Known Activations