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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fid
    -0.06
    ュ
    -0.06
    ेह
    -0.06
    吾
    -0.06
    ],[
    -0.05
    iddle
    -0.05
    workers
    -0.05
     pool
    -0.05
     νέ
    -0.05
    utures
    -0.05
    POSITIVE LOGITS
     averaged
    0.07
    cter
    0.07
     menacing
    0.06
    rock
    0.06
    Okay
    0.06
     textured
    0.06
     dobr
    0.06
     Suff
    0.06
     parallels
    0.06
    ágenes
    0.06
    Act Density 0.042%

    No Known Activations