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

    Neuronpedia

    INDEX
    Explanations

    clauses and phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ordinarily
    -0.06
    aturday
    -0.06
    .scalablytyped
    -0.06
     جو
    -0.06
    ué
    -0.06
     kicking
    -0.06
     timeZone
    -0.06
    .ob
    -0.06
    ţi
    -0.05
     жал
    -0.05
    POSITIVE LOGITS
    vak
    0.07
    _ASSUME
    0.06
     国家
    0.06
     DH
    0.06
    .tag
    0.06
     pien
    0.06
    -target
    0.06
     کاربر
    0.06
    -neck
    0.06
     ауд
    0.06
    Act Density 0.065%

    No Known Activations