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

    Neuronpedia

    INDEX
    Explanations

    _align

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileName
    -0.07
    .toolStripSeparator
    -0.06
    enumerate
    -0.06
    terní
    -0.06
    letcher
    -0.06
     zejména
    -0.06
    rou
    -0.06
     gridView
    -0.06
    miştir
    -0.06
     denying
    -0.06
    POSITIVE LOGITS
     フ
    0.07
    bew
    0.07
     فعال
    0.07
    ,data
    0.06
    �
    0.06
     カ
    0.06
     تص
    0.06
     जल
    0.06
    시아
    0.06
    asa
    0.06
    Act Density 0.001%

    No Known Activations