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

    Neuronpedia

    INDEX
    Explanations

    relationship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '\
    -0.06
     yararlan
    -0.06
    FileName
    -0.06
     škol
    -0.06
     pře
    -0.06
     evapor
    -0.06
    _pow
    -0.06
    yn
    -0.06
    不好
    -0.06
     policing
    -0.06
    POSITIVE LOGITS
     mechanically
    0.07
     modular
    0.06
    -master
    0.06
     realmente
    0.06
    km
    0.06
    δη
    0.06
    adv
    0.06
    ры
    0.06
    ія
    0.06
    сы
    0.06
    Act Density 0.015%

    No Known Activations