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

    Neuronpedia

    INDEX
    Explanations

    connecting with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ieder
    0.83
     between
    0.83
    between
    0.76
     brackets
    0.73
    krank
    0.72
    ConnectionString
    0.71
     Senators
    0.71
    それぞれの
    0.70
     antara
    0.70
     carers
    0.70
    POSITIVE LOGITS
     üzerinden
    0.70
    ivity
    0.66
    算
    0.65
     Cim
    0.63
    ги
    0.63
    ização
    0.63
     sociology
    0.62
    ervi
    0.62
    рак
    0.62
    iz
    0.62
    Act Density 0.051%

    No Known Activations