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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ियन
    -0.07
    ована
    -0.07
     яких
    -0.07
    productName
    -0.07
    LN
    -0.07
     implicitly
    -0.07
    heimer
    -0.06
    عي
    -0.06
    ्वप
    -0.06
    uely
    -0.06
    POSITIVE LOGITS
     deadliest
    0.06
     данны
    0.06
     ZERO
    0.06
    (samples
    0.05
     Licensing
    0.05
     Last
    0.05
    (Color
    0.05
    _sales
    0.05
    ambient
    0.05
     Decode
    0.05
    Act Density 0.048%

    No Known Activations