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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eight
    -0.07
    álie
    -0.07
    یم
    -0.07
    47
    -0.07
    emi
    -0.06
    backup
    -0.06
    .Blue
    -0.06
    037
    -0.06
    Backup
    -0.06
    EDIUM
    -0.06
    POSITIVE LOGITS
     Serge
    0.07
     Supern
    0.06
     Infer
    0.06
     leash
    0.06
    Adjusted
    0.06
    Concrete
    0.06
    ,arg
    0.06
     dostal
    0.06
     nigeria
    0.06
    rases
    0.06
    Act Density 0.005%

    No Known Activations