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

    Neuronpedia

    INDEX
    Explanations

    more reliable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SIGNED
    0.47
    achievement
    0.45
    Modelo
    0.45
    Casa
    0.45
    మ
    0.45
    鳅
    0.44
    िसोदिया
    0.44
    nick
    0.43
    schema
    0.43
    eating
    0.42
    POSITIVE LOGITS
     elder
    0.42
     apoi
    0.42
     veter
    0.42
     suhu
    0.42
    ρούν
    0.41
     dame
    0.41
     prote
    0.40
     telev
    0.40
     vulve
    0.40
     recipro
    0.40
    Act Density 0.000%

    No Known Activations