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

    Neuronpedia

    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fff
    -0.08
     Jack
    -0.07
     sued
    -0.06
    )')↵
    -0.06
    ugu
    -0.06
    icias
    -0.06
    volt
    -0.06
    anne
    -0.06
    ся
    -0.06
    -Dec
    -0.06
    POSITIVE LOGITS
     р
    0.07
    기준
    0.07
    Wildcard
    0.07
     IMPORTANT
    0.06
    .decorate
    0.06
     isAdmin
    0.06
    pch
    0.06
    setSize
    0.06
     malt
    0.06
    inate
    0.06
    Act Density 0.040%

    No Known Activations