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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forgot
    -0.07
     algebra
    -0.06
     strt
    -0.06
     Paz
    -0.06
     siè
    -0.06
    _entry
    -0.06
    mouse
    -0.06
    ienza
    -0.06
     해
    -0.06
     provoke
    -0.06
    POSITIVE LOGITS
     communion
    0.07
     earnings
    0.07
     Keller
    0.07
     robust
    0.07
     internals
    0.07
     efficacy
    0.06
     governed
    0.06
    comp
    0.06
     Quận
    0.06
    _rng
    0.06
    Act Density 0.002%

    No Known Activations