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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fourteen
    -0.07
     fifteen
    -0.07
     eleven
    -0.07
    	com
    -0.07
     thirteen
    -0.07
    Request
    -0.07
    _KEYBOARD
    -0.06
     strs
    -0.06
     ngồi
    -0.06
    _Reference
    -0.06
    POSITIVE LOGITS
    .
    0.11
    .↵
    0.08
    ]).↵
    0.08
    ”.
    0.08
    .
    0.07
    %.↵
    0.07
    `.↵
    0.07
    =.
    0.07
    .↵↵
    0.07
    .a
    0.07
    Act Density 0.205%

    No Known Activations