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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    comments expressing agreement or approval about societal issues and celebrity behavior.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ूँ
    -0.06
    undefined
    -0.06
    ození
    -0.06
    _wait
    -0.06
     monsters
    -0.06
    :%
    -0.06
    _AN
    -0.06
    κλη
    -0.06
    ifferential
    -0.06
    iese
    -0.06
    POSITIVE LOGITS
     Joint
    0.07
     Hear
    0.07
     W
    0.07
    (Expected
    0.07
    _STRUCT
    0.06
     yy
    0.06
     hosted
    0.06
     Erik
    0.06
     sắc
    0.06
    '],$
    0.06
    Act Density 0.007%

    No Known Activations