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

    Neuronpedia

    INDEX
    Explanations

    vulnerability exploits and technical breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रॉबर्ट
    0.53
    Jwt
    0.45
    AMG
    0.40
    Robert
    0.39
     jums
    0.39
    ائرة
    0.39
     dateFormat
    0.39
     التمرين
    0.38
    olska
    0.38
    Kuota
    0.38
    POSITIVE LOGITS
     component
    0.41
     burn
    0.41
     precipitate
    0.39
     tal
    0.38
     Prop
    0.37
     knowledge
    0.36
     preventative
    0.36
    carriage
    0.36
     organics
    0.36
     giants
    0.35
    Act Density 0.000%

    No Known Activations