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

    Neuronpedia

    INDEX
    Explanations

    hates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stored
    -0.07
     KN
    -0.07
    housing
    -0.07
    عار
    -0.07
    那样
    -0.07
    )\↵
    -0.07
    .reg
    -0.06
    _we
    -0.06
    	  ↵
    -0.06
    -0.06
    POSITIVE LOGITS
    τια
    0.07
    tsx
    0.06
     上海
    0.06
    /create
    0.06
     IsPlainOldData
    0.06
     RTL
    0.06
    RGB
    0.06
    MHz
    0.06
     působ
    0.06
    953
    0.06
    Act Density 0.003%

    No Known Activations