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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    微软雅黑
    -0.07
    526
    -0.07
    880
    -0.07
     cages
    -0.07
     nah
    -0.07
    thank
    -0.06
    ски
    -0.06
    CONS
    -0.06
    -0.06
    服
    -0.06
    POSITIVE LOGITS
    (()=>{↵
    0.07
    	rc
    0.06
     دکتر
    0.06
     reven
    0.06
    .parallel
    0.06
     Idle
    0.06
    Crypto
    0.06
    ={()=>
    0.06
    스의
    0.06
     hypothesis
    0.06
    Act Density 0.003%

    No Known Activations