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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _td
    -0.06
    iat
    -0.06
     cid
    -0.06
    фек
    -0.06
     ro
    -0.06
    /bar
    -0.06
    пат
    -0.06
    fest
    -0.06
    \Table
    -0.06
    odelist
    -0.06
    POSITIVE LOGITS
    мовір
    0.07
     imposs
    0.07
     SVM
    0.07
     사랑
    0.06
    िरफ
    0.06
    _SPELL
    0.06
    iked
    0.06
    �
    0.06
    AMAGE
    0.06
     Ihren
    0.06
    Act Density 0.147%

    No Known Activations