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

    Neuronpedia

    INDEX
    Explanations

    pose, reach, target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uca
    0.30
     fused
    0.29
     eased
    0.29
    нија
    0.27
     relig
    0.27
     ki
    0.27
    जार
    0.27
     linen
    0.27
    fass
    0.27
     steels
    0.27
    POSITIVE LOGITS
    }\\
    0.32
    )\\
    0.31
    :\\
    0.27
    ancipation
    0.27
    .\\
    0.27
    )+(
    0.27
    ).\\
    0.27
    怠
    0.26
    \\
    0.25
    URLException
    0.25
    Act Density 0.000%

    No Known Activations