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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     based
    0.53
    름
    0.49
     latitudes
    0.48
     for
    0.48
    ################
    0.48
    ుల
    0.47
    ید
    0.47
     teman
    0.46
     두
    0.46
     প্ল
    0.46
    POSITIVE LOGITS
    na
    0.59
    ará
    0.53
    '}
    0.52
     vym
    0.52
     deteriorate
    0.52
    nels
    0.52
    inata
    0.50
    ľa
    0.50
     deplete
    0.50
    in
    0.49
    Act Density 0.010%

    No Known Activations