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

    Neuronpedia

    INDEX
    Explanations

    geometric transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    held
    -0.08
     breakout
    -0.07
    regar
    -0.07
     militar
    -0.07
    nut
    -0.07
    ние
    -0.07
     avance
    -0.07
     noodles
    -0.07
    乐
    -0.07
    otros
    -0.07
    POSITIVE LOGITS
     đổi
    0.09
     germs
    0.09
     uwagę
    0.08
     commuters
    0.08
     সকল
    0.08
     hacía
    0.08
     shortest
    0.08
     ')'
    0.08
     সমস্ত
    0.08
     குட
    0.08
    Act Density 0.010%

    No Known Activations