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

    Neuronpedia

    INDEX
    Explanations

    match or matches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satiety
    0.38
    ادہ
    0.38
     Strept
    0.38
     carrier
    0.37
     commenc
    0.37
    queur
    0.37
     ያለው
    0.37
    চৈত
    0.37
    asitriangular
    0.36
     ITU
    0.36
    POSITIVE LOGITS
     matched
    0.59
     matches
    0.58
    匹配
    0.58
    Matches
    0.55
    match
    0.55
    matches
    0.54
    Match
    0.53
    MATCH
    0.53
     match
    0.52
     MATCH
    0.51
    Act Density 0.000%

    No Known Activations