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

    Neuronpedia

    INDEX
    Explanations

    medical research ethics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     copy
    -0.07
     好
    -0.07
    зі
    -0.07
     copying
    -0.07
     forgive
    -0.06
    .parametrize
    -0.06
     birth
    -0.06
     fundraising
    -0.06
     communism
    -0.06
     FILES
    -0.06
    POSITIVE LOGITS
    		
↵		
↵
    0.07
    sizlik
    0.06
     ];↵↵
    0.06
     consequential
    0.06
    ############
    0.06
     Mattis
    0.06
     располож
    0.06
    abilidad
    0.06
    _FORWARD
    0.06
     일부
    0.06
    Act Density 0.005%

    No Known Activations