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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =
↵
    -0.06
    tribution
    -0.06
    .called
    -0.06
     bigger
    -0.06
     کود
    -0.06
     grado
    -0.06
     necessity
    -0.06
    embrance
    -0.06
     HEX
    -0.06
    _fraction
    -0.06
    POSITIVE LOGITS
     Unc
    0.06
    .JOptionPane
    0.06
    宇
    0.06
     zastup
    0.06
    _Save
    0.06
     سام
    0.06
    ดำเน
    0.06
     سپتامبر
    0.06
    0.06
     Enter
    0.05
    Act Density 0.004%

    No Known Activations