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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.40
    ➛
    0.38
    gning
    0.38
    𠃍
    0.38
    nungen
    0.38
     to
    0.37
    ش
    0.36
     digraph
    0.36
    \
    0.35
    nings
    0.34
    POSITIVE LOGITS
    до
    0.38
    <unused1888>
    0.38
    <unused499>
    0.38
    <unused411>
    0.37
     Comité
    0.37
    <unused399>
    0.37
    ↵
    0.36
    <unused402>
    0.36
    <unused311>
    0.35
    <unused300>
    0.35
    Act Density 0.383%

    No Known Activations