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

    Neuronpedia

    INDEX
    Explanations

    strategy or episodes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sole
    0.50
     羽
    0.49
    Intel
    0.49
    }}^{\
    0.49
    }^{\#
    0.49
    Qualifier
    0.48
    有一個
    0.47
    ⌚
    0.47
    Sole
    0.47
    🤐
    0.47
    POSITIVE LOGITS
     επι
    0.63
     sizzling
    0.62
     wszystkim
    0.61
     symbolName
    0.60
     길
    0.60
     hidro
    0.60
     alf
    0.59
     підприєм
    0.59
     bisnis
    0.59
     laranja
    0.59
    Act Density 0.000%

    No Known Activations