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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     balancing
    -0.07
     vielleicht
    -0.06
    考试
    -0.06
     элем
    -0.06
    ombs
    -0.06
    between
    -0.06
     limits
    -0.06
     ö
    -0.06
     averages
    -0.06
    ییر
    -0.06
    POSITIVE LOGITS
     Qu
    0.07
     cach
    0.06
    giatan
    0.06
    фіка
    0.06
    .TextAlignment
    0.06
    rank
    0.06
    มข
    0.06
     qu
    0.06
    _paper
    0.06
     militia
    0.06
    Act Density 0.002%

    No Known Activations