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

    Neuronpedia

    INDEX
    Explanations

    calculate number of eggs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ສາມາດ
    0.44
    ukannya
    0.41
    nodemon
    0.39
    ∽
    0.38
     살펴보도록
    0.38
    ක
    0.38
     있기
    0.38
    하지만
    0.36
    latego
    0.36
    руются
    0.36
    POSITIVE LOGITS
     =
    0.88
    =
    0.77
    }=
    0.66
     $=
    0.65
     resulting
    0.59
    }=$
    0.58
    $=
    0.55
    }=\
    0.55
     $=$
    0.55
    ＝
    0.54
    Act Density 0.120%

    No Known Activations