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

    Neuronpedia

    INDEX
    Explanations

    thank you for your work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     environments
    0.51
     corpses
    0.43
     walled
    0.42
     characters
    0.42
     decomposition
    0.40
     dimensionless
    0.40
     dungeon
    0.39
     symb
    0.39
     correlations
    0.39
    endance
    0.39
    POSITIVE LOGITS
     THANK
    0.55
     मेरा
    0.52
     complicated
    0.51
    咨询
    0.51
     minha
    0.50
    THANK
    0.49
     thank
    0.48
     сложные
    0.47
     mijn
    0.47
     консульта
    0.47
    Act Density 0.031%

    No Known Activations