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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -money
    -0.06
    Major
    -0.06
    862
    -0.06
    κό
    -0.06
    umlu
    -0.06
     Hurricane
    -0.06
    ricane
    -0.06
     Hindus
    -0.06
    ріш
    -0.06
    ivr
    -0.06
    POSITIVE LOGITS
    (period
    0.07
    urovision
    0.07
    quiries
    0.06
     �
    0.06
    >>↵↵
    0.06
    .integration
    0.06
     Lydia
    0.06
                
↵
    0.06
     Oversight
    0.06
     stepping
    0.06
    Act Density 0.018%

    No Known Activations