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

    Neuronpedia

    INDEX
    Explanations

    focus on specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ONDER
    0.44
    汔
    0.44
    δος
    0.43
     muffler
    0.42
     Denison
    0.42
    Wax
    0.42
     Steinmann
    0.42
    陵
    0.42
     Arkadaşlar
    0.42
     Rashford
    0.41
    POSITIVE LOGITS
    ︎
    0.44
    fc
    0.43
     última
    0.43
     >;
    0.42
    >,
    0.41
    クセ
    0.41
     यूनिक
    0.40
    ා
    0.40
    iana
    0.40
    ificación
    0.40
    Act Density 0.003%

    No Known Activations