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

    Neuronpedia

    INDEX
    Explanations

    Hiding or being hidden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accessibility
    -0.07
     juices
    -0.07
    _air
    -0.07
     LX
    -0.07
    (light
    -0.07
    滦
    -0.06
    Medical
    -0.06
    Ill
    -0.06
    内陆
    -0.06
    (RuntimeObject
    -0.06
    POSITIVE LOGITS
    rellas
    0.07
    全新的
    0.07
    펨
    0.07
    🌆
    0.07
    봇
    0.07
    xr
    0.06
    ⏬
    0.06
     hảo
    0.06
    吸引
    0.06
    markdown
    0.06
    Act Density 0.033%

    No Known Activations