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

    Neuronpedia

    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (can
    -0.06
    άνω
    -0.06
     Surre
    -0.06
    .ResultSet
    -0.06
    住
    -0.06
     Прав
    -0.06
     Neutral
    -0.06
    .train
    -0.06
    Ｄ
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
    '
↵
↵
    0.07
     uplat
    0.07
    印
    0.07
    caf
    0.07
     blessed
    0.06
     Australia
    0.06
    .tab
    0.06
    _al
    0.06
     moth
    0.06
    ph
    0.06
    Act Density 0.045%

    No Known Activations