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

    Neuronpedia

    INDEX
    Explanations

    spoilers, storm, persin, predictably

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SMP
    0.40
     DMP
    0.39
     SMP
    0.38
    παϊ
    0.38
     DMG
    0.37
    太
    0.37
     paž
    0.37
    ymmetric
    0.37
     SDI
    0.37
    牺
    0.36
    POSITIVE LOGITS
     causas
    0.45
     monumento
    0.44
     fifteen
    0.42
    akaranam
    0.41
    ལ་
    0.40
    쏘
    0.39
    динку
    0.38
    hamento
    0.38
     fissures
    0.38
     quarant
    0.38
    Act Density 0.001%

    No Known Activations