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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _br
    -0.07
    ちょっと
    -0.06
    illus
    -0.06
     وا
    -0.06
    裝
    -0.06
     در
    -0.06
    .drawText
    -0.06
     della
    -0.06
    .www
    -0.06
    ьют
    -0.06
    POSITIVE LOGITS
     which
    0.08
     Chem
    0.07
     само
    0.07
     that
    0.07
    :↵↵
    0.06
     misleading
    0.06
     cells
    0.06
     karakter
    0.06
     contamin
    0.06
     Shall
    0.06
    Act Density 0.118%

    No Known Activations