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

    Neuronpedia

    INDEX
    Explanations

    here's a plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఎంత
    0.43
     неиз
    0.40
     Nahin
    0.40
    mainframe
    0.40
     Utilizing
    0.40
    airement
    0.39
     посредством
    0.39
    Appending
    0.38
     Apica
    0.38
    ろう
    0.37
    POSITIVE LOGITS
    ,\\
    0.38
    ูก
    0.37
     bouquet
    0.37
    ቻ
    0.37
     hint
    0.36
     &\
    0.36
     resa
    0.35
     earthy
    0.35
     wyjątk
    0.35
     bitter
    0.35
    Act Density 0.001%

    No Known Activations