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
     KL
    -0.07
    อนท
    -0.06
     Christ
    -0.06
     breakfast
    -0.06
    (R
    -0.06
     Heights
    -0.06
     Rak
    -0.06
     Path
    -0.06
    _vk
    -0.06
    _lng
    -0.06
    POSITIVE LOGITS
    _cube
    0.07
    母
    0.07
     strav
    0.06
     oyn
    0.06
     ella
    0.06
    �性
    0.06
     Jug
    0.06
    нения
    0.06
    .checkBox
    0.06
     pena
    0.06
    Act Density 0.003%

    No Known Activations