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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
                                   ↵
    -0.08
    Vel
    -0.07
    isha
    -0.07
     Sens
    -0.07
     Rey
    -0.07
     LayoutInflater
    -0.07
    혜
    -0.07
     Swe
    -0.06
    越好
    -0.06
     parental
    -0.06
    POSITIVE LOGITS
     rang
    0.07
     function
    0.07
     рад
    0.07
     purpose
    0.07
     f
    0.07
     RAT
    0.07
    脂肪
    0.06
     F
    0.06
    伍
    0.06
     SqlCommand
    0.06
    Act Density 0.062%

    No Known Activations