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

    Neuronpedia

    INDEX
    Explanations

    quantified statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विभिन्न
    0.46
    easily
    0.46
     épaisse
    0.46
    𒀸
    0.46
     காட்சி
    0.46
     찾
    0.45
     fácil
    0.44
     diminue
    0.44
    𝐬
    0.44
     राक्ष
    0.43
    POSITIVE LOGITS
     networking
    0.39
     http
    0.38
    めに
    0.37
    ഭം
    0.37
     lines
    0.37
     Services
    0.37
     networks
    0.36
    HAS
    0.36
    REFERENCES
    0.35
     welfare
    0.35
    Act Density 0.000%

    No Known Activations