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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric expressions (digits and decimal‐style numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	X
    -0.07
     regexp
    -0.06
     Versions
    -0.06
     psychologically
    -0.06
    íl
    -0.06
    lm
    -0.06
    ete
    -0.06
     sulph
    -0.06
    とする
    -0.06
    572
    -0.06
    POSITIVE LOGITS
    (APP
    0.07
     ↑
    0.07
     enf
    0.06
    inou
    0.06
    งแรก
    0.06
    턴
    0.06
     Races
    0.06
     UserRole
    0.06
     Gould
    0.06
     Stud
    0.06
    Act Density 0.083%

    No Known Activations