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

    Neuronpedia

    INDEX
    Explanations

    Self-compassion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arty
    -0.09
     nylon
    -0.08
     Telecommunications
    -0.08
    782
    -0.08
     trabajos
    -0.08
    ৬
    -0.08
    čeno
    -0.07
    -six
    -0.07
     telecommunications
    -0.07
     tələb
    -0.07
    POSITIVE LOGITS
     compassion
    0.12
     kindness
    0.12
     forgive
    0.11
     mercy
    0.11
     forgiveness
    0.11
     Compassion
    0.10
     compassionate
    0.10
     siebie
    0.10
     miseric
    0.09
     forgiving
    0.09
    Act Density 0.015%

    No Known Activations