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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raj
    -0.08
     Roh
    -0.07
    major
    -0.07
    자동
    -0.07
    ійської
    -0.06
    padding
    -0.06
     minHeight
    -0.06
     Shah
    -0.06
    Azure
    -0.06
    .Transform
    -0.06
    POSITIVE LOGITS
    存档
    0.07
     Ammo
    0.07
    _FRE
    0.06
     अच
    0.06
    驾
    0.06
     patt
    0.06
     kích
    0.06
    llx
    0.06
    ":@"
    0.06
    assertTrue
    0.06
    Act Density 0.012%

    No Known Activations