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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oxfordshire
    -0.90
    richTextPanel
    -0.79
     Dorset
    -0.73
    shire
    -0.71
     Montana
    -0.69
     OREGON
    -0.66
    IsMutable
    -0.66
    Montana
    -0.65
     Warwickshire
    -0.62
     Odisha
    -0.61
    POSITIVE LOGITS
     Offisielt
    0.52
     Settle
    0.51
    łaś
    0.47
     Peut
    0.47
     Efq
    0.46
     firent
    0.46
     Cis
    0.44
    Settle
    0.44
    ądź
    0.43
    ędziesz
    0.42
    Act Density 0.127%

    No Known Activations