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

    Neuronpedia

    INDEX
    Explanations

    you prompts who come initiates like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.50
     esté
    0.49
    e
    0.48
     materialize
    0.45
     admire
    0.45
    ஃப்
    0.45
     incluem
    0.44
     incluye
    0.43
     Então
    0.43
     È
    0.43
    POSITIVE LOGITS
    😞
    0.48
    ؟؟
    0.47
    λη
    0.46
     ನನಗೆ
    0.45
     imposition
    0.43
     लापरवाही
    0.43
    𒄭
    0.43
    कौन
    0.43
    निर्माण
    0.43
    焼け
    0.41
    Act Density 0.007%

    No Known Activations