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

    Neuronpedia

    INDEX
    Explanations

    presence and avoiding distractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approximate
    -0.08
    _pal
    -0.08
     Hits
    -0.08
    _small
    -0.08
     PASS
    -0.07
    _hit
    -0.07
     SMALL
    -0.07
     Pass
    -0.07
    _PASS
    -0.07
     Pul
    -0.07
    POSITIVE LOGITS
    angent
    0.09
     careg
    0.08
     cellphone
    0.08
     unplug
    0.08
     laptop
    0.08
     engross
    0.08
     jantar
    0.08
     allocated
    0.08
     종료
    0.08
    ending
    0.08
    Act Density 0.014%

    No Known Activations