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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etherlands
    -0.08
    ;k
    -0.07
     led
    -0.06
    "));↵
    -0.06
     wreck
    -0.06
    Co
    -0.06
     harder
    -0.06
    ====
    -0.06
    icides
    -0.06
     Primer
    -0.06
    POSITIVE LOGITS
    险
    0.07
     richt
    0.06
    enting
    0.06
    інг
    0.06
    態
    0.06
    かって
    0.06
     PROT
    0.06
     타
    0.06
     Relay
    0.06
     Dost
    0.06
    Act Density 0.000%

    No Known Activations