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

    Neuronpedia

    INDEX
    Explanations

    Sadness and negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     physicists
    -0.07
     Auditor
    -0.06
     chicken
    -0.06
    -mode
    -0.06
    ์ค
    -0.06
    _raises
    -0.06
    なんて
    -0.06
    [state
    -0.06
     Electronics
    -0.06
    .Settings
    -0.06
    POSITIVE LOGITS
    meter
    0.07
    ceed
    0.06
    quired
    0.06
     gerekiyor
    0.06
    Really
    0.06
    .toolStripMenuItem
    0.06
     dors
    0.06
    assert
    0.06
     çay
    0.06
     바이
    0.06
    Act Density 0.077%

    No Known Activations