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

    Neuronpedia

    INDEX
    Explanations

    uncertainty or speculation

    np_max-act · gemini-2.0-flash

    The neuron fires on the discourse particle “though,” i.e. adversative/concessive uses of “though.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    貝
    -0.07
     phishing
    -0.07
     metre
    -0.07
    glm
    -0.06
     annihil
    -0.06
    psi
    -0.06
    )did
    -0.06
     Hardcore
    -0.06
     Jess
    -0.06
     bitch
    -0.06
    POSITIVE LOGITS
    _RANGE
    0.07
    Role
    0.06
     lòng
    0.06
    播放
    0.06
    iệng
    0.06
     leží
    0.06
     คน
    0.06
    Fed
    0.06
     безопас
    0.06
    .option
    0.05
    Act Density 0.098%

    No Known Activations