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

    Neuronpedia

    INDEX
    Explanations

    supply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ProductName
    -0.07
     craft
    -0.07
    摸
    -0.06
     coerc
    -0.06
    erty
    -0.06
     Uganda
    -0.06
    ульт
    -0.06
     biting
    -0.06
    _entity
    -0.06
     PERFORMANCE
    -0.06
    POSITIVE LOGITS
     supplied
    0.07
     supply
    0.07
     raided
    0.07
    NSMutableArray
    0.07
    [arr
    0.06
    .layers
    0.06
     supplying
    0.06
     дав
    0.06
     stronger
    0.06
     arise
    0.06
    Act Density 0.054%

    No Known Activations