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

    Neuronpedia

    INDEX
    Explanations

    between achieving or maximizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viruses
    0.44
    妈妈
    0.38
     virus
    0.38
    Instead
    0.38
     frumo
    0.36
    Original
    0.36
    病毒
    0.36
    呈现
    0.35
     coronae
    0.35
     Viruses
    0.35
    POSITIVE LOGITS
    ład
    0.42
     chamber
    0.41
    ARIO
    0.40
     orientação
    0.39
    leather
    0.38
     poolside
    0.38
    deck
    0.38
    ED
    0.38
    ario
    0.38
    pool
    0.38
    Act Density 0.003%

    No Known Activations