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

    Neuronpedia

    INDEX
    Explanations

    feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    っぱ
    -0.07
     ομάδα
    -0.07
    (order
    -0.07
    ницы
    -0.06
    below
    -0.06
    
    -0.06
    _rd
    -0.06
    .getDay
    -0.06
     override
    -0.06
     aggression
    -0.06
    POSITIVE LOGITS
    ITTER
    0.07
     expr
    0.06
    umsuz
    0.06
     mutlu
    0.06
    -current
    0.06
     Δι
    0.06
            ↵
    0.06
     Çalış
    0.06
    -big
    0.06
     ліка
    0.06
    Act Density 0.106%

    No Known Activations