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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kel
    -0.06
     tb
    -0.06
     luk
    -0.06
    _UNICODE
    -0.06
    models
    -0.06
     cô
    -0.06
    bank
    -0.06
     oste
    -0.06
    .currency
    -0.06
    ertiary
    -0.06
    POSITIVE LOGITS
     увелич
    0.07
     الل
    0.07
    orgot
    0.06
     informace
    0.06
     елек
    0.06
    :'',
    0.06
    Fluid
    0.06
    ?>&
    0.06
     capitalize
    0.06
    Ordered
    0.06
    Act Density 0.013%

    No Known Activations