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

    Neuronpedia

    INDEX
    Explanations

    4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒔
    0.38
    𝘀
    0.35
     silently
    0.34
     this
    0.34
    йын
    0.33
     ולא
    0.33
    ...',
    0.33
    ра
    0.33
    ⠑
    0.33
    ,
    0.32
    POSITIVE LOGITS
    athyroid
    0.32
    9
    0.32
    ⃣
    0.31
    ِّف
    0.29
     eukaryotic
    0.29
    addPreferredGap
    0.29
     grandes
    0.28
    palindrome
    0.28
    5
    0.28
     mathvariant
    0.28
    Act Density 0.069%

    No Known Activations