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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    us
    -0.07
     products
    -0.07
     Initially
    -0.06
     kernels
    -0.06
    ือน
    -0.06
    Src
    -0.06
     své
    -0.06
    город
    -0.06
     Tale
    -0.06
     kernel
    -0.06
    POSITIVE LOGITS
    نسان
    0.07
     Й
    0.06
     Leicester
    0.06
    尔
    0.06
     NotificationCenter
    0.06
    akhstan
    0.06
    lator
    0.06
    爾
    0.06
     Seb
    0.06
     Hä
    0.06
    Act Density 0.024%

    No Known Activations