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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /audio
    -0.07
     padd
    -0.07
    руш
    -0.07
    	layer
    -0.07
     washer
    -0.06
    _ACK
    -0.06
     nächsten
    -0.06
    -lines
    -0.06
    u
    -0.06
    	
↵
↵
    -0.06
    POSITIVE LOGITS
     utilise
    0.07
    TextStyle
    0.06
     Wilkinson
    0.06
     نفت
    0.06
    ㅋㅋㅋㅋ
    0.06
    religious
    0.05
     onCancel
    0.05
    mekte
    0.05
    兴
    0.05
    -Semit
    0.05
    Act Density 0.022%

    No Known Activations