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

    Neuronpedia

    INDEX
    Explanations

    agreement, cafe, bank, fee, purchase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ą
    1.05
    text
    1.01
    éu
    1.00
    n
    1.00
    ка
    0.96
    recommend
    0.95
    natural
    0.95
    OR
    0.94
    ită
    0.93
    flickr
    0.91
    POSITIVE LOGITS
     serde
    0.92
    ))).
    0.80
    ექტ
    0.77
     CMV
    0.77
    )$$
    0.77
    IRED
    0.76
     amplitudes
    0.75
     jaanu
    0.74
     경우가
    0.74
     TID
    0.73
    Act Density 0.001%

    No Known Activations