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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лиц
    -0.07
    לג
    -0.07
     Identification
    -0.07
    وه
    -0.07
     Distrib
    -0.07
    лок
    -0.07
    汤
    -0.07
     blogger
    -0.06
    made
    -0.06
    .True
    -0.06
    POSITIVE LOGITS
     Vinyl
    0.07
    铆
    0.07
    훜
    0.07
    ₪
    0.07
     ##↵
    0.06
    .isVisible
    0.06
    חדשות
    0.06
    主力
    0.06
     psychedelic
    0.06
     expertise
    0.06
    Act Density 0.017%

    No Known Activations