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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indre
    -0.07
    .Default
    -0.07
    бор
    -0.07
     Rei
    -0.07
    -enter
    -0.07
    生怕
    -0.07
    �
    -0.07
     Independ
    -0.06
    tsky
    -0.06
     thập
    -0.06
    POSITIVE LOGITS
    RODUCTION
    0.08
    ,row
    0.08
    Species
    0.08
    Com
    0.07
     withObject
    0.07
    特派员
    0.07
    published
    0.07
     permissions
    0.07
    〉
    0.07
     screenplay
    0.07
    Act Density 0.003%

    No Known Activations