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

    Neuronpedia

    INDEX
    Explanations

    -width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jur
    -0.08
     tới
    -0.07
    滿
    -0.07
    Terr
    -0.07
     '%"
    -0.07
    Mono
    -0.06
    Jul
    -0.06
    ，一
    -0.06
     三
    -0.06
     keine
    -0.06
    POSITIVE LOGITS
    OD
    0.06
    ыв
    0.06
     prescribed
    0.06
     deformation
    0.06
     kz
    0.06
    pecially
    0.06
     automatic
    0.06
     kilometers
    0.06
     conducted
    0.06
     consumes
    0.06
    Act Density 0.002%

    No Known Activations