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

    Neuronpedia

    INDEX
    Explanations

    fluent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zij
    -0.07
    �
    -0.07
    ILTER
    -0.06
     liber
    -0.06
     基
    -0.06
    birth
    -0.06
    OUCH
    -0.06
    .Zip
    -0.06
    ibia
    -0.06
    \Storage
    -0.06
    POSITIVE LOGITS
     fluent
    0.18
     Fluent
    0.14
    uent
    0.10
     कभ
    0.09
    fluence
    0.08
     concurrent
    0.08
     flurry
    0.07
     Meet
    0.07
    Frozen
    0.07
    .Threading
    0.07
    Act Density 0.003%

    No Known Activations