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

    Neuronpedia

    INDEX
    Explanations

    specific items and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indole
    0.49
    frak
    0.48
    inverse
    0.48
    invert
    0.47
    ana
    0.45
     матри
    0.44
     রাস
    0.43
     Ρ
    0.43
    নাশ
    0.43
     versa
    0.43
    POSITIVE LOGITS
    Semif
    0.46
    セミナー
    0.45
     Solids
    0.44
    Shortly
    0.44
     பேச்சு
    0.43
    மேலும்
    0.42
    Holiday
    0.42
     Drying
    0.42
     Computers
    0.41
    ハム
    0.41
    Act Density 0.000%

    No Known Activations