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

    Neuronpedia

    INDEX
    Explanations

    Library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suffering
    -0.07
     kaz
    -0.06
     Rud
    -0.06
    \Unit
    -0.06
     土
    -0.06
    	task
    -0.06
    (avg
    -0.06
     Ave
    -0.06
     miscon
    -0.06
     Dispose
    -0.06
    POSITIVE LOGITS
     Library
    0.09
     library
    0.07
     librarian
    0.07
    rarian
    0.07
     robin
    0.07
     Ranger
    0.07
    ocking
    0.07
    _backup
    0.07
    ERY
    0.06
    RTOS
    0.06
    Act Density 0.008%

    No Known Activations