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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collectors
    -0.07
     parted
    -0.07
    Therefore
    -0.07
    phones
    -0.06
     Map
    -0.06
    ';↵↵
    -0.06
     Therefore
    -0.06
     dess
    -0.06
     circuits
    -0.06
    ']));↵
    -0.06
    POSITIVE LOGITS
    views
    0.07
    论
    0.07
    stash
    0.06
     тяж
    0.06
     Mystery
    0.06
    дах
    0.06
     Απ
    0.06
    ุณภาพ
    0.06
    ume
    0.06
     рассчит
    0.06
    Act Density 0.033%

    No Known Activations