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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ומה
    -0.08
     Letter
    -0.07
     sex
    -0.07
     valley
    -0.07
     You
    -0.07
    look
    -0.06
     Athena
    -0.06
    大会
    -0.06
    混凝土
    -0.06
    Sun
    -0.06
    POSITIVE LOGITS
    -reset
    0.08
    箧
    0.07
    ят
    0.07
     مستوى
    0.07
     meas
    0.07
     AXIS
    0.07
    솥
    0.07
    จำ
    0.07
    Remote
    0.07
    特长
    0.07
    Act Density 0.001%

    No Known Activations