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

    Neuronpedia

    INDEX
    Explanations

    exceed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    post
    -0.07
    .Inst
    -0.07
     jist
    -0.07
    Dani
    -0.07
     hostages
    -0.07
     ther
    -0.07
     Để
    -0.07
     jmé
    -0.06
    Applications
    -0.06
    POSITIVE LOGITS
     (>
    0.07
     exceed
    0.07
     exceeds
    0.07
     extended
    0.06
    .Count
    0.06
    _expected
    0.06
    fait
    0.06
    redict
    0.06
    .df
    0.06
    (criteria
    0.06
    Act Density 0.005%

    No Known Activations