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

    Neuronpedia

    INDEX
    Explanations

    factors influencing outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +}^{
    0.36
    ina
    0.33
    𝐭
    0.33
    𝐥
    0.32
     Verwendung
    0.31
    varphi
    0.30
    𝐩
    0.30
    ногда
    0.29
    𝐲
    0.29
    নেট
    0.29
    POSITIVE LOGITS
     nilpotent
    0.30
    ்
    0.30
    ườ
    0.29
     ausgestattet
    0.28
     mobilized
    0.28
    Projectile
    0.28
     ionization
    0.28
     superconductors
    0.28
    աս
    0.27
    DropDownStyle
    0.27
    Act Density 0.549%

    No Known Activations