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

    Neuronpedia

    INDEX
    Explanations

    are struggling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hopefully
    0.71
     ple
    0.66
     initially
    0.64
    cox
    0.62
     probably
    0.62
    মির
    0.60
    Del
    0.60
     del
    0.59
    ോള
    0.57
     opioids
    0.57
    POSITIVE LOGITS
     anymore
    0.92
     whatsoever
    0.88
    その他
    0.87
     その他
    0.85
     alcuna
    0.83
     अन्य
    0.82
    permalink
    0.81
     Architektur
    0.81
     आकर्षक
    0.81
    ssid
    0.81
    Act Density 0.092%

    No Known Activations