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

    Neuronpedia

    INDEX
    Explanations

    case insensitive comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    裒
    0.42
     ARR
    0.40
     исте
    0.40
    ści
    0.40
     да
    0.39
     REQUEST
    0.39
     в
    0.38
     से
    0.38
    owanej
    0.38
     компании
    0.38
    POSITIVE LOGITS
    error
    0.40
    love
    0.37
    toolbox
    0.35
    xml
    0.35
     araştırm
    0.35
     것이다
    0.35
    }};
    0.35
    new
    0.34
    script
    0.34
    derive
    0.34
    Act Density 0.001%

    No Known Activations