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

    Neuronpedia

    INDEX
    Explanations

    ideologies and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     while
    0.36
     with
    0.35
     because
    0.34
     despite
    0.33
     during
    0.32
    ”、
    0.31
    与其
    0.31
     as
    0.31
     ద్వారా
    0.31
     whilst
    0.31
    POSITIVE LOGITS
    Ecco
    0.33
    𝗘
    0.33
    מ
    0.31
    Acceler
    0.31
    the
    0.30
    AES
    0.30
    Asc
    0.30
    Milliseconds
    0.30
    Chest
    0.30
    Contributors
    0.30
    Act Density 0.851%

    No Known Activations