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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mann
    -0.08
    ത്തില
    -0.08
    cost
    -0.07
     Isaac
    -0.07
     Infect
    -0.07
     maa
    -0.07
     साबित
    -0.07
     দিয়ে
    -0.07
     magazine
    -0.07
     mucus
    -0.07
    POSITIVE LOGITS
     красав
    0.09
     بهر
    0.08
    lts
    0.08
     ಸೆ
    0.08
     pertains
    0.08
     opoz
    0.08
    batim
    0.08
     Tops
    0.08
    _Long
    0.07
     ವಿವ
    0.07
    Act Density 0.001%

    No Known Activations