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

    Neuronpedia

    INDEX
    Explanations

    statement terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mehr
    0.51
     stessa
    0.49
     hama
    0.49
     तालाब
    0.48
    தம்ப
    0.47
    ποι
    0.46
    ഥ
    0.46
    ха
    0.46
     mudd
    0.45
    infested
    0.45
    POSITIVE LOGITS
    <unused2121>
    0.56
    侎
    0.54
    inely
    0.50
     accounted
    0.49
    崱
    0.49
    sulf
    0.47
    sf
    0.47
    <unused2175>
    0.47
    公益
    0.47
    etting
    0.47
    Act Density 0.131%

    No Known Activations