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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ON
    -0.07
     Our
    -0.07
    .slide
    -0.07
    .createSequentialGroup
    -0.06
     judge
    -0.06
     AB
    -0.06
     Bentley
    -0.06
     fingert
    -0.06
     pay
    -0.06
     inund
    -0.06
    POSITIVE LOGITS
    mah
    0.08
    lahoma
    0.07
    ITICAL
    0.06
    оді
    0.06
    _bag
    0.06
     Bengal
    0.06
     вип
    0.06
    (dispatch
    0.06
    dots
    0.06
    _aut
    0.06
    Act Density 0.022%

    No Known Activations