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

    Neuronpedia

    INDEX
    Explanations

    last names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .BLL
    -0.07
    .titleLabel
    -0.07
     定
    -0.07
     gubern
    -0.07
     Вал
    -0.07
    .neighbors
    -0.07
     grads
    -0.07
     cũ
    -0.07
    .CLASS
    -0.07
    velopment
    -0.07
    POSITIVE LOGITS
     worm
    0.07
     fish
    0.07
     Carp
    0.07
     Fat
    0.07
     Tan
    0.07
    Fat
    0.07
     Fish
    0.07
     tan
    0.07
     poisonous
    0.06
     �
    0.06
    Act Density 0.192%

    No Known Activations