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

    Neuronpedia

    INDEX
    Explanations

    recipe instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /results
    -0.09
    ありが
    -0.08
     exchanging
    -0.08
    osition
    -0.08
    hasil
    -0.08
    嬉
    -0.08
     lawful
    -0.08
     результаты
    -0.08
     chakra
    -0.08
     violating
    -0.08
    POSITIVE LOGITS
     Shakespeare
    0.08
    .Dependency
    0.08
     An
    0.07
    ’m
    0.07
    ’re
    0.07
     Damage
    0.07
     crumbs
    0.07
     bl
    0.07
    lations
    0.07
     שונים
    0.07
    Act Density 0.010%

    No Known Activations