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

    Neuronpedia

    INDEX
    Explanations

    you thanks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Av
    -0.07
    Av
    -0.07
     škola
    -0.07
    irez
    -0.06
    古屋
    -0.06
     burada
    -0.06
     âm
    -0.06
     avantaj
    -0.06
    ional
    -0.06
     Dum
    -0.06
    POSITIVE LOGITS
     furnished
    0.06
    /components
    0.06
     curled
    0.06
    -blood
    0.06
    -word
    0.06
     resurrect
    0.06
    acted
    0.06
    :last
    0.06
    _IList
    0.06
    响
    0.06
    Act Density 0.006%

    No Known Activations