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

    Neuronpedia

    INDEX
    Explanations

    defining scope and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ازی
    0.37
     salud
    0.37
    inig
    0.36
     człowie
    0.36
    azoline
    0.36
     조성
    0.36
    ლ
    0.36
     também
    0.35
    तक
    0.35
     soloist
    0.35
    POSITIVE LOGITS
     margins
    0.46
     caseload
    0.45
     scope
    0.44
     Scope
    0.44
     When
    0.41
     Zones
    0.41
     Avocado
    0.40
     Boundaries
    0.39
     suitcase
    0.39
    Qaeda
    0.39
    Act Density 0.001%

    No Known Activations