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

    Neuronpedia

    INDEX
    Explanations

    xml dependency artifactId

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     architects
    0.42
     applicants
    0.42
    ArchivePath
    0.39
    WorkingDirectory
    0.38
    BUUID
    0.38
     GRADE
    0.38
    olecules
    0.37
    𒆠
    0.37
    াভাবিক
    0.37
     ساتھ
    0.36
    POSITIVE LOGITS
     அம
    0.38
    …</
    0.38
     пребы
    0.38
     सत्या
    0.37
    붕
    0.36
    •
    0.35
    𝟏
    0.35
    elij
    0.34
    மைய
    0.33
     pendek
    0.33
    Act Density 0.000%

    No Known Activations