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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *j
    -0.07
     Trey
    -0.06
    @AllArgsConstructor
    -0.06
    _step
    -0.06
    DrawerToggle
    -0.06
     GenerationType
    -0.06
    OMUX
    -0.06
    rama
    -0.06
    ασ
    -0.06
     legalized
    -0.06
    POSITIVE LOGITS
     cine
    0.07
    \s
    0.07
     discover
    0.07
    Queue
    0.07
     PUS
    0.06
    uttle
    0.06
     عاش
    0.06
     intervening
    0.06
     {
↵
↵
↵
    0.06
    quel
    0.06
    Act Density 0.058%

    No Known Activations