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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ID
    -0.07
    .b
    -0.07
     vanilla
    -0.07
    276
    -0.07
    _s
    -0.07
    Earlier
    -0.06
     briefly
    -0.06
     Until
    -0.06
     přid
    -0.06
    Until
    -0.06
    POSITIVE LOGITS
    出售
    0.06
    ційно
    0.06
    <typename
    0.06
    ัตน
    0.06
     بودن
    0.06
    formulario
    0.06
    (serializers
    0.06
    础
    0.06
    <footer
    0.06
    iềm
    0.06
    Act Density 0.034%

    No Known Activations