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

    Neuronpedia

    INDEX
    Explanations

    assistant turns ortype of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exhibiting
    0.40
    extensive
    0.39
     utilising
    0.39
     environs
    0.36
     exhibits
    0.36
     करें
    0.35
     atop
    0.35
     numerose
    0.35
     striving
    0.34
     endeavours
    0.34
    POSITIVE LOGITS
     साल
    0.39
     знай
    0.37
     생각을
    0.36
    গিরই
    0.36
     सबक
    0.36
     Justice
    0.35
    Justice
    0.35
     그렇게
    0.35
     habíamos
    0.35
    Just
    0.35
    Act Density 0.001%

    No Known Activations