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

    Neuronpedia

    INDEX
    Explanations

    code generation requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Velocity
    0.38
     Canon
    0.35
     Caffeine
    0.34
     उदाहरण
    0.34
     Lutheran
    0.32
     limitée
    0.31
     AngularJS
    0.31
    ısında
    0.31
    ANG
    0.30
    렜
    0.30
    POSITIVE LOGITS
    보기
    0.37
     intitul
    0.36
     estiver
    0.35
    ringar
    0.35
    titled
    0.34
     entitled
    0.33
     titled
    0.33
     kuin
    0.33
    Wrap
    0.32
    solve
    0.32
    Act Density 0.007%

    No Known Activations