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
    /downloads
    -0.07
     Woche
    -0.06
     Algebra
    -0.06
     appending
    -0.06
    Ế
    -0.06
    AVED
    -0.06
    istique
    -0.06
     barren
    -0.06
     machen
    -0.06
    ιώ
    -0.06
    POSITIVE LOGITS
    _cn
    0.07
    (cm
    0.07
     businesses
    0.07
    _pp
    0.06
     supervisor
    0.06
    身
    0.06
     VP
    0.06
     DI
    0.06
    	tx
    0.06
     excitement
    0.06
    Act Density 0.005%

    No Known Activations