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

    Neuronpedia

    INDEX
    Explanations

    interpreted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptest
    -0.07
    -vertical
    -0.07
     služby
    -0.06
     stehen
    -0.06
     Tommy
    -0.06
    (pthread
    -0.06
    -written
    -0.06
    list
    -0.06
    ]._
    -0.06
    ัญห
    -0.06
    POSITIVE LOGITS
    [],
    0.07
    Attachments
    0.07
     compreh
    0.06
     outpatient
    0.06
     coherent
    0.06
     intric
    0.06
     Yorkers
    0.06
     lubric
    0.06
    zioni
    0.06
    .concat
    0.06
    Act Density 0.010%

    No Known Activations