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

    Neuronpedia

    INDEX
    Explanations

    relationship building and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visualization
    0.42
     Fon
    0.42
    reper
    0.40
    ouvrage
    0.37
    ܩ
    0.37
    ீர
    0.37
     শক্তিশালী
    0.37
     REPORTER
    0.37
     reporters
    0.36
    ഴി
    0.36
    POSITIVE LOGITS
    交流
    0.63
     tacit
    0.62
     intimate
    0.62
    暧
    0.60
     intimacy
    0.58
     서로
    0.57
    沟通
    0.56
    默
    0.55
    互相
    0.54
    曖
    0.54
    Act Density 0.008%

    No Known Activations