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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PS
    -0.07
     Ki
    -0.07
     volume
    -0.06
     comparison
    -0.06
    ani
    -0.06
     Officials
    -0.06
    ']="
    -0.06
     Rankings
    -0.06
     
    -0.06
    Judge
    -0.06
    POSITIVE LOGITS
     жив
    0.07
    xlsx
    0.06
    NSSet
    0.06
    exemple
    0.06
     печ
    0.06
    Simply
    0.06
    جه
    0.06
    ,!
    0.06
     Emerald
    0.06
    طر
    0.06
    Act Density 0.001%

    No Known Activations