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

    Neuronpedia

    INDEX
    Explanations

    479

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sie
    -0.08
     Sok
    -0.07
     Slo
    -0.07
     Sek
    -0.06
    sys
    -0.06
     ascending
    -0.06
     lieutenant
    -0.06
    SI
    -0.06
     SVN
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    481
    0.09
    47
    0.08
    480
    0.07
    courses
    0.07
    478
    0.07
    479
    0.07
     ظ
    0.07
    486
    0.07
    -watch
    0.06
    ;]/
    0.06
    Act Density 0.059%

    No Known Activations