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

    Neuronpedia

    INDEX
    Explanations

    features or capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kum
    0.42
    änn
    0.42
    warl
    0.41
    Destroy
    0.39
    Needless
    0.38
    なんだ
    0.38
    ಗೋ
    0.38
    ர்த்த
    0.37
     Casting
    0.37
     মম
    0.37
    POSITIVE LOGITS
     వ్య
    0.40
    ,"$
    0.40
     वही
    0.38
    ,...,
    0.38
     Grat
    0.37
    受益
    0.36
    +...+
    0.36
    閑
    0.36
     GRAT
    0.35
     Split
    0.35
    Act Density 0.000%

    No Known Activations