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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еп
    -0.07
    boro
    -0.06
     booster
    -0.06
     bare
    -0.06
    มนตร
    -0.06
     ayar
    -0.06
    adian
    -0.06
    ouv
    -0.06
     selections
    -0.06
    26
    -0.06
    POSITIVE LOGITS
    [key
    0.07
     weiter
    0.07
     повинні
    0.07
    '^$',
    0.07
    ([$
    0.07
     Geoff
    0.06
    关键
    0.06
     название
    0.06
     amusing
    0.06
    /node
    0.06
    Act Density 0.008%

    No Known Activations