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

    Neuronpedia

    INDEX
    Explanations

    petroleum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inscription
    -0.07
    missing
    -0.07
    融合发展
    -0.07
    猢
    -0.07
    ⊇
    -0.07
    现出
    -0.07
    intersection
    -0.07
    舛
    -0.06
    ⾝
    -0.06
    一瞬间
    -0.06
    POSITIVE LOGITS
     Profile
    0.07
     awareness
    0.07
    :\"
    0.07
     mask
    0.07
    的力量
    0.07
    ЛЬ
    0.07
     ;
↵
↵
    0.06
     granularity
    0.06
    nap
    0.06
    dom
    0.06
    Act Density 0.037%

    No Known Activations