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

    Neuronpedia

    INDEX
    Explanations

    predicting consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ming
    0.47
     ISSN
    0.45
    Ming
    0.45
    स्तो
    0.44
     de
    0.43
     influential
    0.43
    Modify
    0.41
    Pseudo
    0.41
     LUC
    0.41
    Ethnic
    0.41
    POSITIVE LOGITS
     overworked
    0.47
    觕
    0.47
     robbing
    0.47
     welded
    0.46
     ancak
    0.46
     تاہم
    0.45
     elytris
    0.45
     smears
    0.45
    ujjati
    0.45
    を通して
    0.44
    Act Density 0.004%

    No Known Activations