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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wt
    -0.07
     bursting
    -0.07
     longitude
    -0.07
    صر
    -0.06
     kos
    -0.06
    ROUP
    -0.06
     seizure
    -0.06
     rent
    -0.06
    Criterion
    -0.06
    entrant
    -0.06
    POSITIVE LOGITS
     Safe
    0.06
    async
    0.06
    Bachelor
    0.06
    _UDP
    0.06
     Africans
    0.06
    \Config
    0.06
    Color
    0.06
     Επι
    0.06
     African
    0.06
    RELATED
    0.06
    Act Density 0.000%

    No Known Activations