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

    Neuronpedia

    INDEX
    Explanations

    hem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [])
↵
    -0.07
    lando
    -0.07
    ıcı
    -0.07
    news
    -0.06
    ватися
    -0.06
    细胞
    -0.06
    -good
    -0.06
    Markup
    -0.06
    Technology
    -0.06
    Turkey
    -0.06
    POSITIVE LOGITS
    aupt
    0.07
    	glm
    0.06
    IGHT
    0.06
     battalion
    0.06
    ’am
    0.06
    yang
    0.06
     latent
    0.06
     captain
    0.06
    279
    0.06
    .Parse
    0.06
    Act Density 0.002%

    No Known Activations