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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nombreux
    1.70
    disamb
    1.66
    opaedia
    1.63
    agaman
    1.61
    大規模
    1.56
    岂
    1.55
    際は
    1.55
     newVal
    1.54
     numerosi
    1.53
    埠
    1.52
    POSITIVE LOGITS
    ened
    1.95
    ening
    1.71
    hearted
    1.68
    ish
    1.65
    headed
    1.59
     hearted
    1.58
    erc
    1.52
    él
    1.51
    est
    1.51
    я
    1.50
    Act Density 0.336%

    No Known Activations