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

    Neuronpedia

    INDEX
    Explanations

    Stereotypes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    న
    -0.07
     receipt
    -0.07
     Residence
    -0.07
    饯
    -0.07
    婆
    -0.07
    pageSize
    -0.07
    Marshal
    -0.07
    _CONSOLE
    -0.06
    觉得很
    -0.06
    legates
    -0.06
    POSITIVE LOGITS
    **/↵
    0.08
    "\↵
    0.07
    方式进行
    0.07
     "]";↵
    0.07
    로부터
    0.07
     @"";↵
    0.07
     intersections
    0.07
    ']:↵
    0.06
     hooked
    0.06
     obscene
    0.06
    Act Density 0.093%

    No Known Activations