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

    Neuronpedia

    INDEX
    Explanations

    specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     everybody
    0.68
     �
    0.59
     iedere
    0.59
     illetve
    0.59
     bütün
    0.57
     solamente
    0.56
     loosing
    0.56
    !",
    0.52
     તથા
    0.52
     вследствие
    0.52
    POSITIVE LOGITS
     ​​
    1.55
     XNUMX
    1.20
    ​​
    1.19
     ​​​​
    1.15
    ​​​​
    0.91
    NUMX
    0.65
    .​​
    0.60
    ̵
    0.58
    🇧
    0.53
     તેણીએ
    0.46
    Act Density 0.000%

    No Known Activations