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

    Neuronpedia

    INDEX
    Explanations

    screenshots or images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alendar
    -0.07
    чен
    -0.07
     ave
    -0.07
    VICE
    -0.06
    -four
    -0.06
     III
    -0.06
    оги
    -0.06
    direccion
    -0.06
     '&#
    -0.06
    evity
    -0.06
    POSITIVE LOGITS
    隊
    0.07
    iddled
    0.07
    _trial
    0.06
     вал
    0.06
    ().'/
    0.06
    .rd
    0.06
     Pee
    0.06
     mettre
    0.06
     Bark
    0.06
     decking
    0.06
    Act Density 0.163%

    No Known Activations