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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collected
    -0.07
     larvae
    -0.07
     mir
    -0.06
     ">
    -0.06
     наступ
    -0.06
     fic
    -0.06
     uploading
    -0.06
     世
    -0.06
    .skip
    -0.06
     era
    -0.06
    POSITIVE LOGITS
     birim
    0.07
    ют
    0.06
     schn
    0.06
    od
    0.06
     tanı
    0.06
    ¥
    0.06
     Grocery
    0.06
    ätt
    0.06
    改革
    0.06
    naz
    0.06
    Act Density 0.124%

    No Known Activations