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

    Neuronpedia

    INDEX
    Explanations

    short duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Resolved
    -0.07
    Roz
    -0.07
    ым
    -0.06
    (next
    -0.06
     tor
    -0.06
    机会
    -0.06
    management
    -0.06
     mantra
    -0.06
     Canterbury
    -0.06
     DISPATCH
    -0.06
    POSITIVE LOGITS
     attracts
    0.06
     fleeting
    0.06
     unhealthy
    0.06
    AGO
    0.06
    LObject
    0.06
    +F
    0.06
     (...)
    0.06
     обор
    0.05
     getProperty
    0.05
    라는
    0.05
    Act Density 0.053%

    No Known Activations