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
    身体
    -0.07
    ])*
    -0.07
     pedals
    -0.07
    OSC
    -0.07
    Vect
    -0.07
     QUICK
    -0.06
    .Modified
    -0.06
    bind
    -0.06
    戦
    -0.06
     performances
    -0.06
    POSITIVE LOGITS
    мерикан
    0.06
    ;b
    0.06
    (NAME
    0.06
    '),
↵
    0.06
     strerror
    0.06
     subsidi
    0.06
    ↵
↵
↵
    0.06
     someday
    0.06
     timid
    0.06
     {
↵
    0.06
    Act Density 0.064%

    No Known Activations