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

    Neuronpedia

    INDEX
    Explanations

    ground / grounding / grounded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     söz
    0.38
    ្នែក
    0.34
    蕭
    0.34
    ანი
    0.34
     විශ
    0.32
    ullar
    0.32
    jene
    0.31
    ल्पना
    0.31
    ޟ
    0.30
    жня
    0.30
    POSITIVE LOGITS
     ground
    4.88
     Ground
    4.50
    Ground
    4.47
    ground
    4.34
     GROUND
    4.16
    GROUND
    3.63
     ग्राउंड
    3.58
     grond
    3.34
     grounded
    3.28
     grounding
    3.23
    Act Density 0.094%

    No Known Activations