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

    Neuronpedia

    INDEX
    Explanations

    API key security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _upgrade
    -0.08
     towering
    -0.08
    skyld
    -0.08
     upgraded
    -0.07
    pun
    -0.07
    ெய
    -0.07
     kailangan
    -0.07
     гармони
    -0.07
    ️⃣
    -0.07
     patriarch
    -0.07
    POSITIVE LOGITS
    .hide
    0.10
     وعدم
    0.09
    (hidden
    0.09
    _HIDE
    0.09
    密
    0.09
     hides
    0.09
     hiding
    0.09
    .Hide
    0.08
    	hide
    0.08
     divulgação
    0.08
    Act Density 0.008%

    No Known Activations