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

    Neuronpedia

    INDEX
    Explanations

    geographical regions and legal/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cincin
    -0.89
    皈
    -0.85
    所の
    -0.78
    rowning
    -0.76
    StringLength
    -0.75
    ȴ
    -0.73
     cala
    -0.73
     Glyco
    -0.72
     escuchar
    -0.71
     Sewell
    -0.71
    POSITIVE LOGITS
    KT
    1.11
     KT
    1.07
     Minneapolis
    1.01
     Winnipeg
    0.99
     Manitoba
    0.88
     Minnesota
    0.87
     Prairie
    0.85
    Winnipeg
    0.85
     Dyck
    0.85
     млн
    0.84
    Act Density 0.003%

    No Known Activations