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

    Neuronpedia

    INDEX
    Explanations

    frequently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OVER
    -0.07
     on
    -0.07
     pearls
    -0.07
    �
    -0.07
     Shows
    -0.07
     boil
    -0.07
     utterly
    -0.07
    ,O
    -0.07
     over
    -0.06
    _os
    -0.06
    POSITIVE LOGITS
     frequently
    0.13
     frequent
    0.10
    hort
    0.08
     часто
    0.08
    Electronic
    0.07
    Instant
    0.07
    Credentials
    0.07
     Frequently
    0.07
    instant
    0.07
     Instant
    0.07
    Act Density 0.010%

    No Known Activations