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

    Neuronpedia

    INDEX
    Explanations

    complex vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     operation
    -0.77
     مواليد
    -0.76
    ValueStyle
    -0.71
    хьтан
    -0.69
    Complexity
    -0.60
     oper
    -0.59
    createCanvas
    -0.59
     probability
    -0.59
     impedance
    -0.58
     complexity
    -0.58
    POSITIVE LOGITS
     Baillargeon
    0.56
     Siblings
    0.54
    InitVars
    0.51
     betweenstory
    0.48
    bais
    0.47
     Occupations
    0.46
    dymyr
    0.45
    ◀
    0.45
     similar
    0.44
    atguigu
    0.44
    Act Density 0.058%

    No Known Activations