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
     capito
    -0.59
    bit
    -0.54
    kháu
    -0.54
    варь
    -0.52
     bit
    -0.47
    partial
    -0.47
    Bit
    -0.46
    urez
    -0.46
     så
    -0.45
    谍
    -0.44
    POSITIVE LOGITS
    
    0.94
     فريبيس
    0.93
    expandindo
    0.88
     متعلقه
    0.81
    tvguidetime
    0.81
    ########.
    0.79
    новниш
    0.78
    verwijspagina
    0.78
     تانيه
    0.76
    esModule
    0.76
    Act Density 0.439%

    No Known Activations