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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رؤية
    -0.08
    资助
    -0.08
    lama
    -0.07
    쏱
    -0.07
    忞
    -0.07
     forfe
    -0.07
     związane
    -0.06
     Mormons
    -0.06
    优异
    -0.06
    南极
    -0.06
    POSITIVE LOGITS
    還
    0.07
    مكاف
    0.07
     tank
    0.07
    xFFFFFF
    0.07
     balance
    0.07
    okin
    0.07
    odian
    0.07
     proced
    0.06
     שב
    0.06
     ben
    0.06
    Act Density 0.004%

    No Known Activations