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

    Neuronpedia

    INDEX
    Explanations

    best match or fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secrecy
    0.38
     scrotum
    0.38
     irregularities
    0.37
     उपराष्ट्रपति
    0.37
     ignoreString
    0.36
    బ్బ
    0.36
    perp
    0.35
     fluids
    0.35
     departure
    0.35
     wetlands
    0.35
    POSITIVE LOGITS
     matched
    0.60
    matched
    0.55
    匹配
    0.52
    マッチ
    0.48
     matches
    0.48
     Matches
    0.46
     match
    0.45
    match
    0.45
    ビデオ
    0.44
     Match
    0.42
    Act Density 0.000%

    No Known Activations