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

    Neuronpedia

    INDEX
    Explanations

    card game effects activations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    儩
    0.42
    മാര്‍
    0.41
     системе
    0.40
     thổi
    0.39
     निघा
    0.39
    りました
    0.39
    NEWS
    0.39
    webBrowser
    0.39
    貶
    0.39
    ricate
    0.39
    POSITIVE LOGITS
     LP
    0.41
     Dominican
    0.40
     Ai
    0.39
     activation
    0.38
     burn
    0.38
    LP
    0.37
    //!
    0.36
    Activ
    0.35
     fname
    0.35
     persons
    0.35
    Act Density 0.006%

    No Known Activations