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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Strings
    -0.08
     Minimum
    -0.07
    _wave
    -0.07
     neighbor
    -0.07
     VI
    -0.06
    AO
    -0.06
    ara
    -0.06
     Ampl
    -0.06
    {
↵
    -0.06
    衛
    -0.06
    POSITIVE LOGITS
     právní
    0.06
     PRIVATE
    0.06
    _continuous
    0.06
     dostate
    0.06
     iç
    0.06
     광고
    0.06
     Mär
    0.06
     شوند
    0.06
    �
    0.06
    律宾
    0.06
    Act Density 0.005%

    No Known Activations