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

    Neuronpedia

    INDEX
    Explanations

    what starts questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    0.28
     With
    0.25
     dengan
    0.24
     با
    0.23
     WITH
    0.23
     keiner
    0.23
     வெறும்
    0.23
     selben
    0.23
     ekki
    0.23
     stets
    0.23
    POSITIVE LOGITS
     why
    0.38
     reasons
    0.38
    Why
    0.37
    why
    0.37
    What
    0.36
     what
    0.35
     mengapa
    0.35
    what
    0.34
    为什么
    0.33
    advantages
    0.33
    Act Density 4.484%

    No Known Activations