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

    Neuronpedia

    INDEX
    Explanations

    conditions or requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mik
    0.37
     Unter
    0.36
     Otra
    0.36
     messen
    0.36
     allowed
    0.36
    Codes
    0.35
    Kid
    0.35
     Leb
    0.35
    Bus
    0.35
     කාල
    0.34
    POSITIVE LOGITS
     one
    0.52
     entrambe
    0.45
     BOTH
    0.43
     begge
    0.42
    allOf
    0.41
    俦
    0.41
     quantify
    0.41
     احد
    0.40
     одну
    0.40
     Quantification
    0.40
    Act Density 0.005%

    No Known Activations