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

    Neuronpedia

    INDEX
    Explanations

    product quality control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嬥
    -0.08
     Francis
    -0.07
    .zeros
    -0.07
    优先
    -0.07
     Lawrence
    -0.07
     frankly
    -0.07
    contre
    -0.07
    换成
    -0.07
    >Delete
    -0.06
    ,',
    -0.06
    POSITIVE LOGITS
     embry
    0.08
    该怎么办
    0.08
    amarin
    0.08
    .serv
    0.08
    𝘳
    0.07
    _LR
    0.07
    产业集群
    0.07
     eman
    0.07
    ologist
    0.07
    _ssh
    0.07
    Act Density 0.054%

    No Known Activations