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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    植物
    -0.08
    "For
    -0.07
    舌
    -0.07
    _friend
    -0.06
     Agility
    -0.06
    ファ
    -0.06
    "But
    -0.06
    ”),
    -0.06
     tongues
    -0.06
    kw
    -0.06
    POSITIVE LOGITS
    kommen
    0.07
    ekkür
    0.07
     rozdíl
    0.07
    quartered
    0.06
    -blue
    0.06
     صنعتی
    0.06
    )?.
    0.06
    公開
    0.06
     suyu
    0.06
    leşik
    0.06
    Act Density 0.000%

    No Known Activations