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

    Neuronpedia

    INDEX
    Explanations

    this that

    np_max-act · gemini-2.0-flash

    This neuron does not activate for any input and thus does not detect any specific feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    particularly
    -0.07
     Schultz
    -0.06
     Rud
    -0.06
    Professor
    -0.06
    annabin
    -0.06
    eting
    -0.06
    van
    -0.06
    ARR
    -0.06
     awarded
    -0.06
    ัง
    -0.06
    POSITIVE LOGITS
    ']=
    0.07
    )}"↵
    0.07
    /token
    0.07
    )"},↵
    0.07
    _stderr
    0.06
    })↵
    0.06
     );↵↵
    0.06
    (ErrorMessage
    0.06
    )"↵↵
    0.06
    .insert
    0.06
    Act Density 0.045%

    No Known Activations