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

    Neuronpedia

    INDEX
    Explanations

    online dating profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Extracts
    0.82
    learned
    0.75
     Issued
    0.71
    ኖር
    0.70
    Extract
    0.68
    知识
    0.68
     குறி
    0.66
    extracted
    0.65
     Autor
    0.65
     Aprend
    0.65
    POSITIVE LOGITS
     matching
    1.45
     matches
    1.40
     match
    1.38
     profiles
    1.36
    Match
    1.34
    Matches
    1.33
     matchmaking
    1.32
     Matching
    1.32
    matching
    1.31
    Matching
    1.29
    Act Density 0.139%

    No Known Activations