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

    Neuronpedia

    INDEX
    Explanations

    online forum requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bans
    -0.07
     Buddhist
    -0.06
    facility
    -0.06
    roduction
    -0.06
     sarà
    -0.06
     cold
    -0.06
     advocate
    -0.06
    |null
    -0.06
     rek
    -0.06
     bf
    -0.06
    POSITIVE LOGITS
     Стар
    0.07
     madre
    0.06
    称
    0.06
    ĩa
    0.06
     Weiss
    0.06
     strtok
    0.06
    .Blocks
    0.06
     Clippers
    0.06
     Πρό
    0.06
    ?>>
    0.06
    Act Density 0.003%

    No Known Activations