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

    Neuronpedia

    INDEX
    Explanations

    Deep dive or introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="%
    0.37
     muslim
    0.37
     Muslims
    0.37
    🫂
    0.36
     college
    0.35
    视频
    0.35
     FCM
    0.34
    laus
    0.33
    ❒
    0.33
     মুসলিম
    0.33
    POSITIVE LOGITS
     yolk
    0.57
     yolks
    0.54
     soggy
    0.54
     sizzling
    0.52
     охла
    0.52
     sleigh
    0.51
     hoof
    0.50
     sizz
    0.50
     sweetly
    0.50
     chewy
    0.49
    Act Density 0.133%

    No Known Activations