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

    Neuronpedia

    INDEX
    Explanations

    impacts site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]
    0.58
     }
    0.54
     叶
    0.48
    }
    0.46
     তল
    0.43
     companion
    0.42
     ]
    0.41
    ryk
    0.41
    umbles
    0.40
    )
    0.40
    POSITIVE LOGITS
    ્સ
    0.54
    道の
    0.54
    стоит
    0.52
    ς
    0.52
     શરીર
    0.51
     வைத்திய
    0.50
     править
    0.49
     तालुका
    0.49
     Emeritus
    0.48
     πριν
    0.48
    Act Density 0.000%

    No Known Activations