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

    Neuronpedia

    INDEX
    Explanations

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ог
    -0.06
     hikes
    -0.06
     tươi
    -0.06
    ritos
    -0.06
    -il
    -0.06
     Οκ
    -0.06
     forcibly
    -0.06
     Elaine
    -0.06
     �
    -0.06
     майже
    -0.06
    POSITIVE LOGITS
    "urls
    0.07
    Native
    0.07
     pedest
    0.07
    URRENT
    0.06
    oningen
    0.06
    �
    0.06
    										↵
    0.06
    .setString
    0.06
    weapons
    0.06
     roc
    0.06
    Act Density 0.009%

    No Known Activations