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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (=
    1.05
     preferentially
    1.02
    usually
    1.00
     frecu
    0.97
    (":
    0.92
    .:
    0.92
    ∴
    0.91
    odenum
    0.89
     (%)
    0.88
    を用いて
    0.87
    POSITIVE LOGITS
     newcomers
    1.05
     nobody
    1.03
     niemand
    1.03
     ninguém
    1.01
     отсутствие
    1.00
     anyone
    0.99
     việc
    0.97
     pundits
    0.97
     despite
    0.96
     kilku
    0.96
    Act Density 0.095%

    No Known Activations