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

    Neuronpedia

    INDEX
    Explanations

    trophies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dropdown
    -0.06
    روم
    -0.06
     resist
    -0.06
    利用
    -0.06
    разд
    -0.06
    stride
    -0.06
    561
    -0.05
    路径
    -0.05
     Sele
    -0.05
     обор
    -0.05
    POSITIVE LOGITS
    �
    0.07
     lesser
    0.07
     ис
    0.07
     bol
    0.06
     misguided
    0.06
    EOS
    0.06
    (ml
    0.06
     recep
    0.06
     hunger
    0.06
    InView
    0.06
    Act Density 0.052%

    No Known Activations