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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     увелич
    -0.06
     Bull
    -0.06
     що
    -0.06
     centralized
    -0.06
     sche
    -0.06
     tedious
    -0.06
     formed
    -0.06
    (writer
    -0.06
     thaw
    -0.06
    MarshalAs
    -0.06
    POSITIVE LOGITS
    gradation
    0.07
     كيل
    0.07
    -channel
    0.06
    mic
    0.06
    повід
    0.06
    اس
    0.06
    ighbors
    0.06
     inadequate
    0.06
    pillar
    0.06
    .gb
    0.06
    Act Density 0.019%

    No Known Activations