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

    Neuronpedia

    INDEX
    Explanations

    ym

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [];↵↵
    -0.07
     OVER
    -0.07
    _HAVE
    -0.07
     gilt
    -0.07
    لق
    -0.07
     benefiting
    -0.06
     Over
    -0.06
     필요한
    -0.06
    极
    -0.06
     vlas
    -0.06
    POSITIVE LOGITS
     δημο
    0.06
    xi
    0.06
     customs
    0.06
     tb
    0.06
    dac
    0.05
     Kyoto
    0.05
    manent
    0.05
    rms
    0.05
     Preconditions
    0.05
    Dept
    0.05
    Act Density 0.001%

    No Known Activations