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

    Neuronpedia

    INDEX
    Explanations

    "2" and "half"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ("_
    -0.06
    携
    -0.06
     применя
    -0.06
    StoryboardSegue
    -0.06
    ensaje
    -0.06
    ตอน
    -0.06
    "#
    -0.06
    URLOPT
    -0.06
    ษายน
    -0.06
    POSITIVE LOGITS
     Rodriguez
    0.07
     RW
    0.07
     Payments
    0.06
    white
    0.06
     uv
    0.06
     Hall
    0.06
    tabs
    0.06
     自动生成
    0.06
     pits
    0.06
     augmented
    0.06
    Act Density 0.008%

    No Known Activations