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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Idle
    -0.07
    illac
    -0.07
    mh
    -0.07
    たち
    -0.06
    iliated
    -0.06
    toUpperCase
    -0.06
    　　 　
    -0.06
    층
    -0.06
     сел
    -0.06
    ться
    -0.06
    POSITIVE LOGITS
    妻
    0.07
     Clayton
    0.06
     DONE
    0.06
     Psychiat
    0.06
     urlencode
    0.06
    leshoot
    0.06
     Schiff
    0.06
    權
    0.06
    Indices
    0.06
     manipulating
    0.06
    Act Density 0.005%

    No Known Activations