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

    Neuronpedia

    INDEX
    Explanations

    safety hotline information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सभा
    0.74
     faded
    0.72
     added
    0.70
     greenery
    0.67
     closely
    0.66
    忽
    0.66
     bracing
    0.66
     uph
    0.65
     ऐसी
    0.63
     metaphor
    0.63
    POSITIVE LOGITS
    ల్యే
    0.91
    鞋
    0.81
     nồi
    0.80
     polícia
    0.80
    čke
    0.80
    eree
    0.79
     čega
    0.79
    帑
    0.79
     شدہ
    0.78
    ﻭ
    0.78
    Act Density 0.004%

    No Known Activations