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

    Neuronpedia

    INDEX
    Explanations

    advice or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }^{*}(
    0.42
    COCH
    0.39
     pf
    0.38
     Raw
    0.37
     palmit
    0.36
     Norton
    0.36
    ushed
    0.35
     rotors
    0.35
     wildflowers
    0.35
     způ
    0.35
    POSITIVE LOGITS
     remotely
    0.39
    深い
    0.39
    Ве
    0.38
     Cool
    0.38
    高
    0.38
    施
    0.37
    クール
    0.36
     ನ
    0.36
    ম্ভীর
    0.36
     trailbl
    0.36
    Act Density 0.000%

    No Known Activations