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

    Neuronpedia

    INDEX
    Explanations

    DeepMind names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সত্যাগ্রহ
    0.38
     Monique
    0.35
    Sis
    0.35
    𒄩
    0.34
    שי
    0.34
     ለአ
    0.34
     کیسے
    0.34
    Shi
    0.33
     השי
    0.33
     candied
    0.33
    POSITIVE LOGITS
     Jordan
    0.42
    Jordan
    0.40
     Baker
    0.39
     Roberts
    0.38
    Roberts
    0.36
     простых
    0.36
     rosa
    0.35
     Rosa
    0.35
    rosa
    0.34
     jordan
    0.33
    Act Density 0.013%

    No Known Activations