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

    Neuronpedia

    INDEX
    Explanations

    thermodynamics and entropy

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     Bee
    -0.07
     Tas
    -0.07
    iska
    -0.07
     rewarding
    -0.07
     tapi
    -0.06
     �
    -0.06
    -Mar
    -0.06
    -te
    -0.06
    负面影响
    -0.06
     مر
    -0.06
    POSITIVE LOGITS
    (\"
    0.07
    anio
    0.07
     gettext
    0.07
     kitty
    0.07
    𝓿
    0.07
    有足够的
    0.07
    犍
    0.07
    뷴
    0.07
     dealloc
    0.07
    _sc
    0.06
    Act Density 0.027%

    No Known Activations