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

    Neuronpedia

    INDEX
    Explanations

    Virus detection levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ion
    -0.07
    (md
    -0.07
     mà
    -0.07
    "].(
    -0.06
     nějaké
    -0.06
    
    -0.06
     vận
    -0.06
    肥
    -0.06
    确定
    -0.06
    		  ↵
    -0.06
    POSITIVE LOGITS
     auction
    0.07
     demonstrators
    0.06
    omidou
    0.06
     اهد
    0.06
    interesting
    0.06
    ."]↵
    0.06
     skirm
    0.06
    Comic
    0.06
    thought
    0.06
    .Country
    0.06
    Act Density 0.025%

    No Known Activations