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

    Neuronpedia

    INDEX
    Explanations

    do you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lign
    0.72
     angesch
    0.72
    fasterxml
    0.71
    عة
    0.68
     pernah
    0.68
     filosóf
    0.66
     ৭৭
    0.66
     konular
    0.65
     ৭৮
    0.65
    ﺩ
    0.64
    POSITIVE LOGITS
    soever
    0.79
    )}{\
    0.78
     άλλο
    0.75
    rotated
    0.74
    ments
    0.74
    }></
    0.71
    संक
    0.71
    nect
    0.70
    }/>
    0.70
    >)</
    0.68
    Act Density 0.029%

    No Known Activations