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
    	day
    -0.08
     Алекс
    -0.07
    ・マ
    -0.06
     Angus
    -0.06
     pregunta
    -0.06
     Аль
    -0.06
     개인
    -0.06
     Nez
    -0.06
    Aliases
    -0.06
    _EVT
    -0.06
    POSITIVE LOGITS
    
    0.07
    _transport
    0.07
    fds
    0.06
     ])↵
    0.06
    onet
    0.06
    _hdr
    0.06
    spr
    0.06
    ِم
    0.06
     screams
    0.06
    .getOrder
    0.06
    Act Density 0.001%

    No Known Activations