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

    Neuronpedia

    INDEX
    Explanations

    Safety and regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worse
    -0.08
     boarded
    -0.07
     thế
    -0.07
    _me
    -0.06
    drag
    -0.06
    Mad
    -0.06
     modular
    -0.06
    Up
    -0.06
     Thus
    -0.06
    Watching
    -0.06
    POSITIVE LOGITS
     TBD
    0.07
     pir
    0.07
    -ли
    0.06
     الل
    0.06
    percentage
    0.06
    Cum
    0.06
     line
    0.06
     passive
    0.06
     접
    0.06
    INESS
    0.06
    Act Density 0.020%

    No Known Activations