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

    Neuronpedia

    INDEX
    Explanations

    insurance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enthusiasm
    -0.09
     Invisalign
    -0.08
    >↵
    -0.08
     permission
    -0.08
     tendrás
    -0.08
     coche
    -0.08
    .Fragment
    -0.08
     exam
    -0.07
    >;↵
    -0.07
     enthousiasme
    -0.07
    POSITIVE LOGITS
     બી
    0.09
     ગામ
    0.09
     �
    0.09
    云
    0.09
     drought
    0.09
    .cloud
    0.09
    uttur
    0.09
    クラ
    0.08
     Farmer
    0.08
     remarkably
    0.08
    Act Density 0.004%

    No Known Activations