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

    Neuronpedia

    INDEX
    Explanations

    department of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tall
    0.46
     Tyl
    0.45
    缇
    0.45
     Ta
    0.44
     టి
    0.44
     Common
    0.42
     Та
    0.40
     नारियल
    0.40
     मी
    0.40
     Steady
    0.39
    POSITIVE LOGITS
    Dep
    0.90
    dep
    0.86
     Dep
    0.80
     dep
    0.78
     depo
    0.74
     dép
    0.73
    artment
    0.73
    DEP
    0.67
     depolar
    0.66
     DEP
    0.66
    Act Density 0.017%

    No Known Activations