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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     constructing
    -0.07
     concrete
    -0.07
     youth
    -0.07
    DB
    -0.07
     bloody
    -0.06
    (factory
    -0.06
    нения
    -0.06
     marked
    -0.06
    Database
    -0.06
     leicht
    -0.06
    POSITIVE LOGITS
    /lo
    0.07
    Topic
    0.06
                          ↵
    0.06
     Belize
    0.06
     Playstation
    0.06
    _ALIGN
    0.06
     spanish
    0.06
     таком
    0.06
     �
    0.06
     grado
    0.06
    Act Density 0.231%

    No Known Activations