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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soft
    -0.07
    460
    -0.07
    ('.'
    -0.07
    GROUND
    -0.07
     affluent
    -0.06
    ्प
    -0.06
     Tale
    -0.06
    Okay
    -0.06
    Advanced
    -0.06
    Private
    -0.06
    POSITIVE LOGITS
     to
    0.08
     yı
    0.06
     Clim
    0.06
     tri
    0.06
    CreatedBy
    0.06
     continuously
    0.06
     tirelessly
    0.06
    Download
    0.06
     ід
    0.06
     cort
    0.06
    Act Density 0.046%

    No Known Activations