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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trách
    -0.06
    iado
    -0.06
    404
    -0.06
     gilt
    -0.06
     Rare
    -0.06
    Fax
    -0.06
    ERRQ
    -0.06
     ampl
    -0.05
    立て
    -0.05
    蜜
    -0.05
    POSITIVE LOGITS
     formally
    0.07
    zim
    0.07
    ('>
    0.07
     AVC
    0.07
     هایی
    0.07
     Blick
    0.07
     catastrophe
    0.07
     wander
    0.07
    сов
    0.06
    éri
    0.06
    Act Density 0.003%

    No Known Activations