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

    Neuronpedia

    INDEX
    Explanations

    curtain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phoenix
    -0.07
     Pioneer
    -0.06
     sklearn
    -0.06
    escaped
    -0.06
    Metric
    -0.06
     bỏ
    -0.06
     �
    -0.06
     Kend
    -0.06
    经验
    -0.06
     Springs
    -0.06
    POSITIVE LOGITS
     artículo
    0.07
     ingres
    0.06
    airo
    0.06
    ulan
    0.06
    pression
    0.06
    variation
    0.06
     žal
    0.06
    regation
    0.06
    udden
    0.06
    RESSION
    0.06
    Act Density 0.004%

    No Known Activations