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

    Neuronpedia

    INDEX
    Explanations

    Anatomy and origins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seul
    -0.07
    leck
    -0.07
     einmal
    -0.07
    üsü
    -0.07
     investigator
    -0.07
     bruises
    -0.07
    太太
    -0.07
     zich
    -0.07
    cker
    -0.07
    soever
    -0.07
    POSITIVE LOGITS
    oted
    0.08
     Core
    0.07
     "]";↵
    0.07
    传统
    0.06
    ల
    0.06
    objc
    0.06
    (ai
    0.06
    \db
    0.06
    苹
    0.06
    .itemView
    0.06
    Act Density 0.062%

    No Known Activations