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

    Neuronpedia

    INDEX
    Explanations

    return you expect to get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initial
    0.81
     Loan
    0.80
     Loans
    0.80
     Initial
    0.69
    贷
    0.68
    Loans
    0.64
     Financing
    0.64
     Lending
    0.63
     Trained
    0.63
     remainder
    0.62
    POSITIVE LOGITS
     diskut
    0.93
     encontrarás
    0.91
     itemView
    0.90
     edifici
    0.90
     müm
    0.84
     đc
    0.83
     ganglion
    0.83
     étamines
    0.83
    ᱾
    0.82
     haki
    0.82
    Act Density 0.001%

    No Known Activations