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

    Neuronpedia

    INDEX
    Explanations

    programming terms and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !),
    0.35
    ନ୍
    0.35
    -,
    0.34
    inträ
    0.33
    *,
    0.31
    )、
    0.31
    icially
    0.31
    рі
    0.31
     அல்லது
    0.31
    pyrid
    0.31
    POSITIVE LOGITS
     L
    0.42
    +
    0.42
     C
    0.41
     Mga
    0.41
    0.40
     etc
    0.40
     voila
    0.38
    ↵↵
    0.36
     H
    0.36
     M
    0.36
    Act Density 0.114%

    No Known Activations