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

    Neuronpedia

    INDEX
    Explanations

    Code file headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Validator
    -0.07
    коном
    -0.07
     staveb
    -0.07
     legalize
    -0.07
    违
    -0.06
    lenmesi
    -0.06
    Wild
    -0.06
     lex
    -0.06
     되어
    -0.06
    (serializers
    -0.06
    POSITIVE LOGITS
    işi
    0.07
    ?”
    0.06
     Functions
    0.06
    ?"
    0.06
     mama
    0.06
     jacket
    0.06
    abama
    0.06
     رسید
    0.06
     cannabis
    0.06
    syscall
    0.06
    Act Density 0.000%

    No Known Activations