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

    Neuronpedia

    INDEX
    Explanations

    .Activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kissing
    -0.07
    灭
    -0.07
     riêng
    -0.07
     amort
    -0.07
     باب
    -0.06
     Santos
    -0.06
     Baxter
    -0.06
    Recognizer
    -0.06
    Safe
    -0.06
     तरफ
    -0.06
    POSITIVE LOGITS
    clin
    0.07
    /sys
    0.06
    :start
    0.06
    .context
    0.06
    �
    0.06
     Moved
    0.06
    ]];↵
    0.06
    UGHT
    0.06
     manten
    0.06
    )V
    0.06
    Act Density 0.001%

    No Known Activations