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

    Neuronpedia

    INDEX
    Explanations

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arlos
    0.80
     geweld
    0.78
     website
    0.77
     Website
    0.76
     zach
    0.76
     toolbar
    0.76
     visits
    0.74
     تعمل
    0.73
     url
    0.73
     calls
    0.71
    POSITIVE LOGITS
    છ
    0.78
    ી
    0.73
     preconceived
    0.73
    誒
    0.67
    ↵↵↵↵
    0.66
    Hence
    0.66
     😂😂
    0.65
    的情
    0.65
    ificacion
    0.65
     homicide
    0.65
    Act Density 0.027%

    No Known Activations