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

    Neuronpedia

    INDEX
    Explanations

    lists, bullet points, or numbered items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IUnary
    0.42
     SalesLT
    0.41
    𒂠
    0.41
    ormap
    0.41
    ScriptBuf
    0.41
     IncludeField
    0.40
     libsql
    0.40
    slotBox
    0.39
     endGame
    0.39
     کہیں
    0.39
    POSITIVE LOGITS
    0.40
    2
    0.39
    1
    0.39
     some
    0.37
    Some
    0.37
    But
    0.36
    two
    0.36
    <h2>
    0.36
     various
    0.36
    etc
    0.36
    Act Density 0.984%

    No Known Activations