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

    Neuronpedia

    INDEX
    Explanations

    short social exchanges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appelez
    0.43
     вони
    0.41
     souha
    0.40
     хорошее
    0.40
     они
    0.39
     ಒಳ್ಳ
    0.38
     boire
    0.38
     тем
    0.38
     нового
    0.38
     रझा
    0.38
    POSITIVE LOGITS
     social
    0.44
     Resolve
    0.38
     unresolved
    0.37
     anti
    0.37
    규
    0.37
     Social
    0.37
     sag
    0.37
    Resolve
    0.37
     secular
    0.36
     uży
    0.35
    Act Density 0.000%

    No Known Activations