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

    Neuronpedia

    INDEX
    Explanations

    concluding adjective or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UpInside
    0.44
    嫄
    0.42
    Fair
    0.41
    Hair
    0.40
     authors
    0.39
    Authors
    0.38
    Mask
    0.37
    Vertical
    0.37
     Elijah
    0.37
    ElementSibling
    0.36
    POSITIVE LOGITS
    }.}
    0.43
     fabb
    0.42
    }$}
    0.40
    ''}
    0.40
    -}
    0.40
    }$$
    0.39
    ']}
    0.38
     enfer
    0.37
     dement
    0.37
     chiave
    0.37
    Act Density 0.001%

    No Known Activations