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

    Neuronpedia

    INDEX
    Explanations

    lead to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐭
    1.74
    duled
    1.55
    
    1.54
    𝐧
    1.47
     PBMCs
    1.39
    ography
    1.39
    𝐚
    1.38
    ันทร์
    1.36
    𝐢
    1.34
    據
    1.34
    POSITIVE LOGITS
    fscanf
    1.72
     cabo
    1.49
    ખો
    1.45
     anex
    1.42
     credence
    1.31
     tiempo
    1.31
     další
    1.29
     complica
    1.27
    ן
    1.24
    我又
    1.20
    Act Density 0.088%

    No Known Activations