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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েনার
    0.46
    Generate
    0.46
    AMENTO
    0.45
    BLOCK
    0.45
    HEADER
    0.45
    Block
    0.44
    _
    0.43
    at
    0.43
    EMA
    0.42
    The
    0.42
    POSITIVE LOGITS
     delito
    0.61
    岦
    0.59
     раздра
    0.54
     военно
    0.54
     obsz
    0.52
     doctrina
    0.52
     adj
    0.51
     justiciable
    0.51
     Recol
    0.50
     emph
    0.50
    Act Density 0.000%

    No Known Activations