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

    Neuronpedia

    INDEX
    Explanations

    Comparing different types / options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بنابر
    -0.07
     scoring
    -0.06
    _WEAPON
    -0.06
    背
    -0.06
    .manage
    -0.06
     зелен
    -0.06
     SHE
    -0.06
    ''
    -0.06
    енного
    -0.06
     granny
    -0.06
    POSITIVE LOGITS
     })),↵
    0.07
     ];
    0.07
    space
    0.07
     waterproof
    0.07
    -launch
    0.06
     neck
    0.06
    Head
    0.06
    (messages
    0.06
    .Do
    0.06
    .AUTH
    0.06
    Act Density 0.204%

    No Known Activations