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

    Neuronpedia

    INDEX
    Explanations

    Showing hidden files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standings
    -0.07
    RAINT
    -0.07
     глуб
    -0.06
    ایر
    -0.06
    opacity
    -0.06
    maxLength
    -0.06
    ила
    -0.06
    _degree
    -0.06
    یت
    -0.06
    uerdo
    -0.06
    POSITIVE LOGITS
     desn
    0.06
    -nil
    0.06
    fel
    0.06
    風
    0.06
    .login
    0.06
    .inc
    0.06
    /sample
    0.06
    手
    0.06
     selfie
    0.06
    不断
    0.06
    Act Density 0.025%

    No Known Activations