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

    Neuronpedia

    INDEX
    Explanations

    multi-prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    涹
    0.39
     مفید
    0.38
    ನನ್ನು
    0.37
    Hay
    0.37
    婫
    0.36
    addPreferred
    0.35
    精华
    0.35
    hla
    0.34
    不到
    0.34
    QAry
    0.34
    POSITIVE LOGITS
     multi
    1.05
     mult
    0.95
     Multi
    0.95
    Multi
    0.93
    MULTI
    0.84
    multi
    0.82
     sclerosis
    0.82
    faceted
    0.79
     multib
    0.78
     faceted
    0.78
    Act Density 0.028%

    No Known Activations