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

    Neuronpedia

    INDEX
    Explanations

    Replacing/obscuring text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checking
    -0.08
     senso
    -0.08
     strøm
    -0.07
     sentido
    -0.07
    -0.07
     af
    -0.07
     rio
    -0.07
     mortal
    -0.07
     natuurlijke
    -0.07
     Je
    -0.07
    POSITIVE LOGITS
     обознач
    0.11
     placeholder
    0.11
    placeholder
    0.11
     remplacer
    0.10
     remplac
    0.10
    replacement
    0.09
    .placeholder
    0.09
    替
    0.09
    _placeholder
    0.09
     대신
    0.09
    Act Density 0.011%
    No Known Activations