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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     */)
    -0.07
    .fetch
    -0.06
     multim
    -0.06
     cohort
    -0.06
     mapa
    -0.06
    ataset
    -0.06
     abnormalities
    -0.06
    usto
    -0.06
     pathname
    -0.06
     dereg
    -0.06
    POSITIVE LOGITS
    п
    0.07
     exceeds
    0.06
     Huang
    0.06
    _avg
    0.06
    PLEMENT
    0.06
    ні
    0.06
    _inicio
    0.06
     Noah
    0.06
     <
    0.06
    нения
    0.06
    Act Density 0.012%

    No Known Activations