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

    Neuronpedia

    INDEX
    Explanations

    explain capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏯
    0.44
    庁
    0.41
     Desk
    0.39
    LLCATS
    0.38
     диамет
    0.38
    ڕۆ
    0.38
     ብቻ
    0.37
    োলজি
    0.37
     Durchmesser
    0.37
     অক্ষরে
    0.37
    POSITIVE LOGITS
     strip
    0.49
     karma
    0.39
    karma
    0.39
    Stanford
    0.38
     conversion
    0.38
     linguistic
    0.38
    jes
    0.37
     Strip
    0.37
     stup
    0.37
     young
    0.37
    Act Density 0.000%

    No Known Activations