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

    Neuronpedia

    INDEX
    Explanations

    locality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frage
    -0.08
     관심
    -0.08
    手続き
    -0.07
    焦点
    -0.07
     intimidation
    -0.07
     notorious
    -0.07
     delicious
    -0.07
    煲
    -0.07
     flavour
    -0.07
     biochemical
    -0.07
    POSITIVE LOGITS
     libr
    0.07
    fter
    0.07
     Corporation
    0.07
    存放
    0.07
     Pearl
    0.06
     concert
    0.06
     schl
    0.06
     baby
    0.06
    /bin
    0.06
    成人
    0.06
    Act Density 0.028%

    No Known Activations