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

    Neuronpedia

    INDEX
    Explanations

    technical import/export sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attn
    0.43
    जापुर
    0.39
    嗲
    0.37
     البدايه
    0.36
     escrito
    0.35
     अटे
    0.35
     말이
    0.34
    꺄
    0.34
     badań
    0.33
     padres
    0.33
    POSITIVE LOGITS
    ABC
    0.42
    Export
    0.40
    export
    0.39
    abc
    0.38
    <h2>
    0.36
    Exports
    0.36
    સમ
    0.36
    Using
    0.36
    GRAPH
    0.35
    Import
    0.35
    Act Density 0.022%

    No Known Activations