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

    Neuronpedia

    INDEX
    Explanations

    any or anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.55
    。.
    1.47
    ।
    1.40
    ™.
    1.38
    ։
    1.35
    .}
    1.34
    '.
    1.32
    }.
    1.31
    .).
    1.31
    .[
    1.31
    POSITIVE LOGITS
     any
    1.59
     ANY
    1.44
     anything
    1.28
     ANYTHING
    1.25
     or
    1.19
    any
    1.14
    anything
    1.11
    任何
    1.10
     quelconque
    1.10
     particularly
    1.10
    Act Density 0.304%

    No Known Activations