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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wohl
    -0.07
     Wend
    -0.06
     Radi
    -0.06
     bouquet
    -0.06
     Req
    -0.06
    ////////////////////////////////
    -0.06
     derivative
    -0.06
     サ
    -0.06
    '])↵↵↵
    -0.06
     VID
    -0.06
    POSITIVE LOGITS
    ่อไป
    0.07
     Blocks
    0.06
     jit
    0.06
     config
    0.06
    -so
    0.06
    ールド
    0.06
     профессиональ
    0.06
    ahun
    0.06
    ожд
    0.06
    NdEx
    0.06
    Act Density 0.012%

    No Known Activations