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

    Neuronpedia

    INDEX
    Explanations

    actions, behaviors, descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也
    0.77
          
    0.75
     也
    0.75
                       
    0.72
           
    0.70
    0.70
     จึง
    0.68
             
    0.68
     //
    0.67
    考虑到
    0.67
    POSITIVE LOGITS
    চিব
    0.67
    iados
    0.66
     Tiffany
    0.65
    팅
    0.64
     fool
    0.62
     alimony
    0.62
     Natale
    0.62
    inelli
    0.62
     Fool
    0.62
     mustang
    0.62
    Act Density 0.015%

    No Known Activations