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

    Neuronpedia

    INDEX
    Explanations

    invitations to participate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idiom
    0.38
     sintomi
    0.37
     pochod
    0.37
    FName
    0.34
     getValue
    0.34
     ներ
    0.33
     болу
    0.33
    症状
    0.33
     yöntem
    0.33
     pyar
    0.33
    POSITIVE LOGITS
     forces
    0.93
     join
    0.89
     joined
    0.88
     joins
    0.83
    join
    0.82
    Join
    0.79
     Join
    0.79
     ranks
    0.75
    forces
    0.75
     forças
    0.73
    Act Density 0.005%

    No Known Activations