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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("#
    -0.07
    .gold
    -0.06
     мист
    -0.06
    änn
    -0.06
     Bryan
    -0.06
    orneys
    -0.06
    όγ
    -0.06
     gj
    -0.06
    .Match
    -0.06
    erson
    -0.06
    POSITIVE LOGITS
     BufferedWriter
    0.07
     unavailable
    0.06
     discriminatory
    0.06
     customary
    0.06
     پزشکی
    0.06
    095
    0.06
     unable
    0.06
    主
    0.06
     asynchronous
    0.06
     Nowadays
    0.06
    Act Density 0.010%

    No Known Activations