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

    Neuronpedia

    INDEX
    Explanations

    but/However

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鱽
    -0.08
     pest
    -0.07
     kiếm
    -0.07
    陕西
    -0.07
    箧
    -0.07
     أبو
    -0.06
    把自己
    -0.06
    inch
    -0.06
    .—
    -0.06
    之城
    -0.06
    POSITIVE LOGITS
    .Azure
    0.08
    \',
    0.07
     jeune
    0.07
     diagnosed
    0.07
     eag
    0.07
    VERN
    0.07
     设
    0.07
    QUENCE
    0.07
    /TR
    0.07
    𥖨
    0.07
    Act Density 0.060%

    No Known Activations