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

    Neuronpedia

    INDEX
    Explanations

    end of statement or argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =[-
    0.47
    }=[
    0.45
    [['
    0.43
    =\{\
    0.42
    쿱
    0.41
    ='{{
    0.41
    ⟧
    0.41
    =\{
    0.40
     [$
    0.40
     [['
    0.40
    POSITIVE LOGITS
    .");
    0.47
    )");
    0.46
    RH
    0.43
    。”
    0.41
    ");
    0.40
    Parent
    0.39
    ochen
    0.39
    .”
    0.38
    )")
    0.38
    borg
    0.38
    Act Density 0.002%

    No Known Activations