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

    Neuronpedia

    INDEX
    Explanations

    initial atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ル
    0.54
    ت
    0.51
    Beautiful
    0.50
    Feeling
    0.48
    styling
    0.48
    ل
    0.47
    Styl
    0.46
    فيذ
    0.45
    Wiring
    0.45
    DEFINITION
    0.44
    POSITIVE LOGITS
     antes
    0.53
     दर
    0.48
     babys
    0.47
     글로
    0.45
    Tex
    0.44
     tex
    0.44
     acess
    0.44
    terra
    0.43
     apresenta
    0.43
     მოს
    0.43
    Act Density 0.001%

    No Known Activations