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

    Neuronpedia

    INDEX
    Explanations

    various hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ังสือ
    0.42
    𝗨
    0.42
     प्रिया
    0.41
    萛
    0.40
    Fy
    0.40
     博
    0.39
    тори
    0.39
    ᱩ
    0.38
     phê
    0.38
     завжди
    0.38
    POSITIVE LOGITS
     Feel
    0.45
     Get
    0.42
    el
    0.41
    del
    0.41
    ts
    0.40
     Emp
    0.40
     Feels
    0.40
     Pam
    0.40
     Lance
    0.40
     fl
    0.39
    Act Density 0.000%

    No Known Activations