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
     зрозум
    -0.06
    atedRoute
    -0.06
     dry
    -0.06
    ερμαν
    -0.06
    Oops
    -0.06
    ầu
    -0.06
    [test
    -0.06
    три
    -0.06
    mort
    -0.06
    ремя
    -0.06
    POSITIVE LOGITS
    145
    0.07
    846
    0.06
     teleport
    0.06
     princess
    0.06
     BigInteger
    0.06
    toBeTruthy
    0.06
    بیر
    0.06
    -secret
    0.06
    �
    0.06
     surpass
    0.06
    Act Density 0.000%

    No Known Activations