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

    Neuronpedia

    INDEX
    Explanations

    organizations and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘴
    1.05
     VLAN
    0.95
     인한
    0.95
     Mosque
    0.94
     Wadi
    0.92
     구간
    0.92
     яй
    0.91
    𝘻
    0.91
     적용
    0.90
     금액
    0.90
    POSITIVE LOGITS
     specializing
    1.00
    礻
    0.98
    }=\
    0.97
     hired
    0.96
    埋
    0.96
    administered
    0.94
    whose
    0.93
    ్‌
    0.91
    Downward
    0.90
    тың
    0.90
    Act Density 0.175%

    No Known Activations