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

    Neuronpedia

    INDEX
    Explanations

    appetizers and tapas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.16
    nova
    1.07
    ﯽ
    1.02
     ihe
    1.01
    вели
    1.00
    ﺎ
    1.00
    tools
    0.96
    тят
    0.96
    의
    0.95
     ragazzo
    0.95
    POSITIVE LOGITS
     researched
    1.20
     mandated
    1.09
     served
    1.05
     chanted
    1.02
     penalized
    1.01
     metabolized
    0.98
     versed
    0.96
     valid
    0.96
     picked
    0.96
     mechanized
    0.95
    Act Density 0.010%

    No Known Activations