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

    Neuronpedia

    INDEX
    Explanations

    answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Within
    -0.07
     fw
    -0.06
    -part
    -0.06
    Transform
    -0.06
                     
    -0.06
    ASE
    -0.06
     GRAPH
    -0.06
    (cs
    -0.06
    >Date
    -0.06
    وپ
    -0.06
    POSITIVE LOGITS
     треть
    0.07
    Cog
    0.07
     highs
    0.06
     haben
    0.06
     Sophie
    0.06
    USART
    0.06
    _flush
    0.06
     hava
    0.06
     UIAlertController
    0.06
    pesan
    0.06
    Act Density 0.002%

    No Known Activations