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

    Neuronpedia

    INDEX
    Explanations

    Email snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Miranda
    -0.07
     сказав
    -0.07
     watchdog
    -0.07
     toen
    -0.06
    Propagation
    -0.06
     Penis
    -0.06
     CAD
    -0.06
    ขณะท
    -0.06
    ntity
    -0.06
     Vườn
    -0.06
    POSITIVE LOGITS
    ($
    0.07
     summaries
    0.06
    .</
    0.06
    иболее
    0.06
    ‚
    0.06
    bery
    0.06
     lev
    0.06
    गर
    0.06
    ografie
    0.06
    atures
    0.06
    Act Density 0.023%

    No Known Activations