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

    Neuronpedia

    INDEX
    Explanations

    anime/manga

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ales
    -0.07
     chicago
    -0.06
    ंत
    -0.06
    UTH
    -0.06
     KK
    -0.06
    	errors
    -0.06
     Option
    -0.06
    涨
    -0.06
    drink
    -0.06
     Bereich
    -0.06
    POSITIVE LOGITS
     fl
    0.07
    /social
    0.07
     sn
    0.07
    67
    0.06
     سید
    0.06
    _loop
    0.06
     hugs
    0.06
    _mirror
    0.06
     compiling
    0.06
     bo
    0.06
    Act Density 0.005%

    No Known Activations