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

    Neuronpedia

    INDEX
    Explanations

    claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reflect
    0.69
    internal
    0.69
     Pencil
    0.65
    適切
    0.64
    INTERNAL
    0.64
     reflect
    0.63
     thoughtfulness
    0.62
    蒞
    0.62
    দিক
    0.62
     deciduous
    0.61
    POSITIVE LOGITS
     claims
    2.28
     claimed
    2.04
     claim
    2.01
     Claims
    1.97
     claiming
    1.86
     Claim
    1.83
     purported
    1.83
    Claims
    1.81
    Claim
    1.70
     purporting
    1.66
    Act Density 0.669%

    No Known Activations