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

    Neuronpedia

    INDEX
    Explanations

    medical requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pp
    -0.07
     보기
    -0.07
    abilece
    -0.06
     devant
    -0.06
    培训
    -0.06
     Exhibition
    -0.06
     lhs
    -0.06
     membuat
    -0.06
    бут
    -0.06
     alguns
    -0.06
    POSITIVE LOGITS
     genocide
    0.07
    uguay
    0.07
    --)
↵
    0.06
    ks
    0.06
    .SelectedIndex
    0.06
    ">'↵
    0.06
     picks
    0.06
    ],[-
    0.06
    深圳
    0.06
     distracted
    0.06
    Act Density 0.079%

    No Known Activations