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

    Neuronpedia

    INDEX
    Explanations

    data annotations for database mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಪಡ
    0.39
     protección
    0.38
    érer
    0.38
    انى
    0.36
    reonine
    0.36
    yrch
    0.35
    вето
    0.35
    窿
    0.35
    ėjo
    0.34
    铰
    0.34
    POSITIVE LOGITS
    Basic
    0.50
    .*;
    0.49
     Element
    0.47
    Element
    0.46
    Id
    0.46
     Basic
    0.45
     id
    0.44
     basic
    0.43
    =',
    0.40
     പഴ
    0.40
    Act Density 0.000%

    No Known Activations