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

    Neuronpedia

    INDEX
    Explanations

    .css

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')";↵
    -0.07
    .Host
    -0.06
     SUM
    -0.06
    ------
    -0.06
    Hon
    -0.06
    <a
    -0.06
    ctrine
    -0.06
    وقيت
    -0.06
    375
    -0.06
    ALSE
    -0.06
    POSITIVE LOGITS
    adia
    0.07
     Egypt
    0.06
    .Measure
    0.06
     Eye
    0.06
     affirmative
    0.06
    .gamma
    0.06
     mojo
    0.06
    찮
    0.06
     Florence
    0.06
     Deserialize
    0.06
    Act Density 0.004%

    No Known Activations