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

    Neuronpedia

    INDEX
    Explanations

    Hire top, Mice found, von Stern, Dow futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keduanya
    -1.03
    tesis
    -1.02
     maleta
    -0.98
     Older
    -0.98
    tribe
    -0.92
    𝗡
    -0.92
    нева
    -0.91
     rápida
    -0.91
    inkov
    -0.90
    洹
    -0.89
    POSITIVE LOGITS
    !
    0.97
    ?
    0.96
    余談
    0.94
    melho
    0.94
    比较好
    0.92
     offiziellen
    0.90
     unbound
    0.89
     afore
    0.88
    CH
    0.85
     furono
    0.85
    Act Density 0.000%

    No Known Activations