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

    Neuronpedia

    INDEX
    Explanations

    exaggerated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    変わ
    -0.07
     adjunct
    -0.07
    	unsigned
    -0.06
     strlen
    -0.06
    vehicle
    -0.06
    ق
    -0.06
    massage
    -0.06
     Sequ
    -0.06
    .setBackgroundResource
    -0.06
    ekk
    -0.05
    POSITIVE LOGITS
    men
    0.07
     ceux
    0.07
     Scient
    0.07
    rial
    0.07
     Bain
    0.07
    orage
    0.06
    нання
    0.06
     lamb
    0.06
    (NAME
    0.06
    呆
    0.06
    Act Density 0.001%

    No Known Activations