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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the first‐person singular pronoun “I” (i.e. occurrences of “I” in the text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    álním
    -0.07
    chant
    -0.06
    akt
    -0.06
    Cold
    -0.06
     Mob
    -0.06
    ische
    -0.06
     Thread
    -0.06
    isch
    -0.06
    انگ
    -0.06
    CHANT
    -0.06
    POSITIVE LOGITS
    .viewDidLoad
    0.07
     hiç
    0.07
     affidavit
    0.07
     багат
    0.06
     сид
    0.06
    ython
    0.06
     mActivity
    0.06
    Hmm
    0.06
     saga
    0.06
     nationality
    0.06
    Act Density 0.027%

    No Known Activations