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

    Neuronpedia

    INDEX
    Explanations

    As mentioned before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xix
    0.45
     повседнев
    0.44
     речи
    0.43
     мене
    0.43
     जयंती
    0.43
     книге
    0.42
     XIX
    0.42
     acontecimientos
    0.42
     следующим
    0.42
     khối
    0.41
    POSITIVE LOGITS
    㝒
    0.46
     variations
    0.43
    et
    0.42
     optional
    0.41
     ways
    0.40
     controls
    0.39
     pretrial
    0.39
     install
    0.38
    ils
    0.38
     installs
    0.37
    Act Density 0.001%

    No Known Activations