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

    Neuronpedia

    INDEX
    Explanations

    addresses and zip codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BCCI
    0.40
     kautta
    0.40
     vững
    0.39
    罟
    0.37
     Riemannian
    0.37
    োক
    0.35
    蒸汽
    0.35
    മൂഹ
    0.35
    Invocation
    0.34
    essoal
    0.34
    POSITIVE LOGITS
     residential
    0.36
    इज
    0.35
     sleepy
    0.35
    XE
    0.35
     whats
    0.35
    FBS
    0.33
     densities
    0.33
     stoked
    0.33
    Ü
    0.33
    ґ
    0.33
    Act Density 0.002%

    No Known Activations