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

    Neuronpedia

    INDEX
    Explanations

    ox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้ก
    -0.07
    Hospital
    -0.07
     incompetent
    -0.06
    MAT
    -0.06
     CONTROL
    -0.06
    Generate
    -0.06
    headline
    -0.06
    Expansion
    -0.06
    Scient
    -0.06
     भग
    -0.06
    POSITIVE LOGITS
     inf
    0.07
     carte
    0.07
     bin
    0.06
     Visit
    0.06
    122
    0.06
     joe
    0.06
     NBA
    0.06
     JDBC
    0.06
    walk
    0.06
     trot
    0.06
    Act Density 0.005%

    No Known Activations