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

    Neuronpedia

    INDEX
    Explanations

    disadvantages or problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    靺
    -0.08
    真爱
    -0.07
     quando
    -0.07
    球员
    -0.07
     לקר
    -0.06
     fare
    -0.06
    Clean
    -0.06
     nov
    -0.06
    �
    -0.06
    .accept
    -0.06
    POSITIVE LOGITS
    맵
    0.07
    กด
    0.07
     yaw
    0.07
     Mayo
    0.07
    מטי
    0.07
    оф
    0.07
    _FRAME
    0.07
    _MD
    0.07
    dirs
    0.07
     Musk
    0.07
    Act Density 0.137%

    No Known Activations