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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    monary
    -0.08
     Dickens
    -0.07
    ϙ
    -0.07
     escalating
    -0.07
    jej
    -0.07
    wl
    -0.07
    咆
    -0.07
     timeframe
    -0.07
    肯定会
    -0.07
    _Show
    -0.07
    POSITIVE LOGITS
    流失
    0.08
     programs
    0.07
    mono
    0.07
     rationale
    0.07
     популяр
    0.07
     conduct
    0.07
     rivers
    0.07
    igmat
    0.07
     mobility
    0.07
     Pols
    0.07
    Act Density 0.093%

    No Known Activations