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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quarantine
    -0.09
     calibre
    -0.08
    izos
    -0.08
    етки
    -0.08
    emis
    -0.08
     рекомендуется
    -0.08
     рекомен
    -0.08
     القادم
    -0.08
     gist
    -0.08
     quarant
    -0.08
    POSITIVE LOGITS
    施設
    0.09
     incurred
    0.08
     crews
    0.08
     Sentence
    0.08
    措施
    0.07
     வழங்க
    0.07
    (paths
    0.07
     ruas
    0.07
     gangs
    0.07
     streets
    0.07
    Act Density 0.006%

    No Known Activations