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

    Neuronpedia

    INDEX
    Explanations

    encourage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _negative
    -0.06
     City
    -0.06
     arrests
    -0.06
     Avoid
    -0.06
    _FF
    -0.06
     negative
    -0.06
    -ts
    -0.06
     savings
    -0.06
     Cave
    -0.06
    fea
    -0.06
    POSITIVE LOGITS
     �
    0.07
    戻
    0.07
     dejting
    0.07
    ÄŸ
    0.06
    	trigger
    0.06
    .makeText
    0.06
     impe
    0.06
     ними
    0.06
     encourage
    0.06
    _PERMISSION
    0.06
    Act Density 0.020%

    No Known Activations