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

    Neuronpedia

    INDEX
    Explanations

    resolutions, feeding, liquid, loops, considerations, QR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ','"+
    0.46
     快
    0.45
    ებულ
    0.43
    0.43
     Beide
    0.42
    0.42
    ంపు
    0.42
     シングル
    0.41
     basados
    0.41
     电
    0.41
    POSITIVE LOGITS
    ↵
    0.64
     fung
    0.51
    O
    0.49
    नो
    0.48
    НО
    0.46
    Image
    0.46
     күн
    0.44
    }
    0.44
    шинство
    0.43
    نون
    0.43
    Act Density 0.000%

    No Known Activations