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

    Neuronpedia

    INDEX
    Explanations

    warm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HasKey
    -0.06
    resident
    -0.06
     rhyth
    -0.06
     distant
    -0.06
    不过
    -0.06
     depress
    -0.06
     racist
    -0.06
    _ud
    -0.06
    otoxic
    -0.06
    inc
    -0.06
    POSITIVE LOGITS
    *****↵↵
    0.07
    .plot
    0.07
     phí
    0.07
    ...]
    0.06
    。”↵↵
    0.06
     mein
    0.06
     záb
    0.06
    ”。↵↵
    0.06
     Neighbor
    0.06
    	document
    0.06
    Act Density 0.005%

    No Known Activations