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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لئے
    -0.58
     Their
    -0.57
     their
    -0.48
     lij
    -0.48
    returnType
    -0.48
    所需的
    -0.48
     usah
    -0.47
     dulu
    -0.47
     ...
    -0.47
     rodzaju
    -0.47
    POSITIVE LOGITS
     practice
    0.84
    Abitanti
    0.79
    practice
    0.71
     Practice
    0.69
     cases
    0.68
     practicing
    0.67
     practising
    0.67
     Waray
    0.65
     Practi
    0.64
     itself
    0.63
    Act Density 0.005%

    No Known Activations