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

    Neuronpedia

    INDEX
    Explanations

    json structure or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opined
    0.41
    লোড
    0.38
     thisTrack
    0.38
    าระ
    0.37
     tracking
    0.36
     climbing
    0.36
    рованное
    0.36
     umur
    0.36
    xref
    0.35
     Pieter
    0.35
    POSITIVE LOGITS
    Luke
    0.40
    툭
    0.39
    aglia
    0.39
    idy
    0.37
     transferencia
    0.37
    ipage
    0.36
    ハン
    0.36
    াম
    0.35
    dus
    0.35
    zag
    0.35
    Act Density 0.012%

    No Known Activations