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

    Neuronpedia

    INDEX
    Explanations

    fe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    043
    -0.07
     autonomous
    -0.06
    �
    -0.06
     сп
    -0.06
     pou
    -0.06
     ต
    -0.06
     introdu
    -0.06
     position
    -0.06
    _initialized
    -0.06
     ordinance
    -0.06
    POSITIVE LOGITS
     IReadOnly
    0.08
    .health
    0.08
    fee
    0.08
    fe
    0.08
    ifax
    0.07
    _best
    0.07
    τικής
    0.07
    熟
    0.07
    velle
    0.07
    Heart
    0.06
    Act Density 0.003%

    No Known Activations