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

    Neuronpedia

    INDEX
    Explanations

    If/home/influence contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    0.49
    Tab
    0.41
     References
    0.41
    GitHub
    0.41
    ด
    0.40
    Development
    0.40
    File
    0.39
    Complexity
    0.39
    Throughout
    0.39
    Location
    0.39
    POSITIVE LOGITS
     proteger
    0.50
     estr
    0.46
    escol
    0.46
     intolerance
    0.46
     profiter
    0.46
     filtre
    0.46
     viser
    0.46
     riduzione
    0.46
     temporada
    0.46
     bakter
    0.46
    Act Density 0.007%

    No Known Activations