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
    enerative
    -0.07
     Slide
    -0.07
    ."','".$
    -0.07
     total
    -0.07
     vô
    -0.07
    duce
    -0.07
    \Doctrine
    -0.07
     #-}↵
    -0.06
    ":"
    -0.06
    ‟
    -0.06
    POSITIVE LOGITS
    יקר
    0.07
     sık
    0.07
     buena
    0.07
     kinky
    0.07
     timp
    0.07
     ganz
    0.07
    سياس
    0.06
     Hawaii
    0.06
    &amp
    0.06
    线上
    0.06
    Act Density 0.007%

    No Known Activations