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

    Neuronpedia

    INDEX
    Explanations

    Animal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mej
    -0.07
    bero
    -0.07
     touring
    -0.06
    undler
    -0.06
    chop
    -0.06
     ulož
    -0.06
    essa
    -0.06
     thinkers
    -0.06
    -Cs
    -0.06
    anela
    -0.06
    POSITIVE LOGITS
    <c
    0.07
    №№№№
    0.07
    (xi
    0.07
    responseData
    0.07
     às
    0.07
    ่
    0.06
    .CON
    0.06
     tolerate
    0.06
    巴
    0.06
    looks
    0.06
    Act Density 0.002%

    No Known Activations