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

    Neuronpedia

    INDEX
    Explanations

    nagging or haunting thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ляться
    0.39
     PHY
    0.38
    phy
    0.38
     hypert
    0.38
    蓑
    0.38
     डिवा
    0.37
    renergic
    0.37
    hua
    0.37
    forget
    0.35
    манов
    0.35
    POSITIVE LOGITS
     haunting
    1.18
     nagging
    1.16
     haunt
    1.14
     haunted
    1.07
     haunts
    1.07
     lingering
    1.03
     nigg
    0.97
     lingers
    0.97
     gn
    0.95
     lingered
    0.94
    Act Density 0.064%

    No Known Activations