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

    Neuronpedia

    INDEX
    Explanations

    mu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﮇ
    -0.08
    (AdapterView
    -0.07
    ’:
    -0.07
     위해서
    -0.06
    loyd
    -0.06
    ued
    -0.06
    ﯭ
    -0.06
    (View
    -0.06
    ទ
    -0.06
    ጄ
    -0.06
    POSITIVE LOGITS
     electro
    0.07
    Kitchen
    0.07
    -conf
    0.07
    .clean
    0.07
    coeff
    0.07
     opinions
    0.07
    👍
    0.06
     backstory
    0.06
    Warm
    0.06
    -n
    0.06
    Act Density 0.002%

    No Known Activations