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

    Neuronpedia

    INDEX
    Explanations

    introduces concepts or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     select
    0.40
     Delete
    0.39
    শুর
    0.38
    roxine
    0.38
    bracht
    0.38
    िश्वत
    0.37
    select
    0.37
     approbation
    0.37
     talisman
    0.36
     halve
    0.36
    POSITIVE LOGITS
    …</
    0.48
     будут
    0.42
     मोड
    0.42
    ,…
    0.41
     desenho
    0.40
    …
    0.40
    …,
    0.40
    Ком
    0.39
    𝙲
    0.39
     heavier
    0.39
    Act Density 0.000%

    No Known Activations