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

    Neuronpedia

    INDEX
    Explanations

    Buildings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    付き
    -0.07
     irradi
    -0.07
     ith
    -0.06
    rossover
    -0.06
    Celebr
    -0.06
    ربه
    -0.06
     oral
    -0.06
     radi
    -0.06
    _virtual
    -0.06
    rá
    -0.06
    POSITIVE LOGITS
     économ
    0.07
     ",↵
    0.07
     ```↵
    0.06
     autocomplete
    0.06
     Quest
    0.06
     конферен
    0.06
    ΑΚ
    0.06
     )↵
    0.06
     možné
    0.06
    move
    0.06
    Act Density 0.000%

    No Known Activations