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

    Neuronpedia

    INDEX
    Explanations

    Hollow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UBLE
    -0.07
    лось
    -0.06
    ढ
    -0.06
    <-
    -0.06
    "));
↵
↵
    -0.06
    VM
    -0.06
     seks
    -0.06
    iked
    -0.06
    age
    -0.06
    ения
    -0.06
    POSITIVE LOGITS
    แนะนำ
    0.07
     Cout
    0.07
     autres
    0.07
    ]=[
    0.06
     showcase
    0.06
     Kauf
    0.06
    .assertIsNot
    0.06
    OutOfRange
    0.06
     Shard
    0.06
     wxString
    0.06
    Act Density 0.176%

    No Known Activations