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

    Neuronpedia

    INDEX
    Explanations

    acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่าค
    -0.06
     preschool
    -0.06
    XH
    -0.06
    енка
    -0.06
    .fs
    -0.06
     sticks
    -0.06
    ignal
    -0.06
    Gap
    -0.06
     stabilized
    -0.05
    lasses
    -0.05
    POSITIVE LOGITS
     otras
    0.07
    ACA
    0.07
     {}↵↵
    0.06
    /******/↵
    0.06
     Hurt
    0.06
     */↵↵↵↵
    0.06
    Doing
    0.06
     constraint
    0.06
     \""
    0.06
    ulmuş
    0.06
    Act Density 0.022%

    No Known Activations