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

    Neuronpedia

    INDEX
    Explanations

    Norway municipalities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Delete
    -0.07
     위
    -0.07
    .Getter
    -0.07
    -winning
    -0.06
     ocas
    -0.06
    _wire
    -0.06
    .poi
    -0.06
     New
    -0.06
     теперь
    -0.06
     turret
    -0.06
    POSITIVE LOGITS
    947
    0.07
    NullOr
    0.07
    규
    0.07
    phans
    0.06
    -slot
    0.06
     Sage
    0.06
    STRUCTION
    0.06
    954
    0.06
     Cathy
    0.06
    溶
    0.06
    Act Density 0.012%

    No Known Activations