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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     mina
    -0.08
    -0.08
    athon
    -0.08
     Nk
    -0.08
     medida
    -0.08
    -0.07
    ，截至
    -0.07
    .measure
    -0.07
    版
    -0.07
    POSITIVE LOGITS
     schooling
    0.09
     experimentation
    0.09
     Gro
    0.08
     fruitful
    0.08
     подряд
    0.08
     boyunca
    0.08
     동안
    0.08
     పాటు
    0.08
     eating
    0.08
    eps
    0.08
    Act Density 0.038%
    No Known Activations