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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash

    instances of the first-person pronoun "I" (self-references by the assistant).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     cyclists
    -0.07
    _co
    -0.07
    _col
    -0.07
    -ob
    -0.06
    _input
    -0.06
    695
    -0.06
    (callback
    -0.06
     increment
    -0.06
    unto
    -0.06
    .runners
    -0.06
    POSITIVE LOGITS
    Tue
    0.06
    ekkür
    0.06
     milfs
    0.06
     STACK
    0.06
    Tại
    0.06
     saturated
    0.06
    KeyType
    0.06
    Infinity
    0.06
     bolster
    0.06
     suk
    0.05
    Act Density 0.108%

    No Known Activations