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

    Neuronpedia

    INDEX
    Explanations

    conversation turns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    0.59
    Solving
    0.54
    Akt
    0.50
    Testing
    0.50
    antiate
    0.48
    SQL
    0.48
    解决
    0.47
    Profiling
    0.46
    Motivation
    0.46
    Invalid
    0.46
    POSITIVE LOGITS
    <end_of_turn>
    0.86
     cheeky
    0.57
     centenary
    0.57
    êté
    0.56
    दिष्ट
    0.55
     woodland
    0.55
    Meer
    0.55
     plă
    0.54
    媚
    0.54
    婭
    0.54
    Act Density 0.269%

    No Known Activations