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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、市
    -0.08
     kwart
    -0.07
     führen
    -0.07
    ögen
    -0.07
    ેર
    -0.07
     verm
    -0.07
    waters
    -0.07
     אחר
    -0.07
     chines
    -0.07
    ，北京
    -0.07
    POSITIVE LOGITS
     pregnancies
    0.08
     дальнейшем
    0.08
     Consequently
    0.08
    Len
    0.07
    ahrt
    0.07
     سپس
    0.07
    oup
    0.07
     thereby
    0.07
     Megan
    0.07
     Ampl
    0.07
    Act Density 0.237%

    No Known Activations