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

    Neuronpedia

    INDEX
    Explanations

    halls, turrets, foam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ROHAN
    0.52
     DELHI
    0.51
     BLUEN
    0.51
     QnrB
    0.51
    യും
    0.50
     Eropa
    0.48
     JUAN
    0.48
    DIG
    0.48
     upto
    0.47
     déclar
    0.47
    POSITIVE LOGITS
    o
    0.56
    ad
    0.54
    in
    0.50
    over
    0.49
    distance
    0.48
    sequence
    0.47
    cont
    0.45
    Sequence
    0.44
    as
    0.44
    itudinal
    0.44
    Act Density 0.000%

    No Known Activations