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

    Neuronpedia

    INDEX
    Explanations

    size and fit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cost
    -0.07
     forn
    -0.06
     vamp
    -0.06
    _encode
    -0.06
     bru
    -0.06
    ("&
    -0.06
    Dyn
    -0.06
    ).↵↵
    -0.06
     niche
    -0.06
     thiểu
    -0.06
    POSITIVE LOGITS
    mand
    0.07
    ((
    0.07
     loginUser
    0.07
     minha
    0.07
    (sol
    0.06
     estamos
    0.06
    permit
    0.06
    シー
    0.06
     fatalError
    0.06
    .slim
    0.06
    Act Density 0.008%

    No Known Activations