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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quir
    -0.07
    hos
    -0.06
    uition
    -0.06
     Prints
    -0.06
     Gaz
    -0.06
     полов
    -0.06
     vari
    -0.06
     závod
    -0.06
     sluts
    -0.06
     inauguration
    -0.06
    POSITIVE LOGITS
    (Double
    0.07
    	total
    0.07
     stun
    0.07
     discovery
    0.07
    ЎыџN
    0.07
     Gerard
    0.06
     geliştir
    0.06
     chinese
    0.06
    Impossible
    0.06
     shipping
    0.06
    Act Density 0.005%

    No Known Activations