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

    Neuronpedia

    INDEX
    Explanations

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ci
    -0.07
     欧
    -0.07
    Ci
    -0.07
     geographic
    -0.07
    ูไ
    -0.06
    uve
    -0.06
    ồi
    -0.06
     kromě
    -0.06
    ування
    -0.06
     jó
    -0.06
    POSITIVE LOGITS
     rather
    0.16
    rather
    0.12
     Rather
    0.11
     eher
    0.08
    Rather
    0.08
     Raiders
    0.07
    ather
    0.07
     Arkansas
    0.07
     담
    0.06
     decidedly
    0.06
    Act Density 0.006%

    No Known Activations