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

    Neuronpedia

    INDEX
    Explanations

    trade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    코
    -0.07
    =[],
    -0.06
    nv
    -0.06
     slavery
    -0.06
     Frequency
    -0.06
    =Y
    -0.06
     Why
    -0.06
     elements
    -0.06
     inconsistency
    -0.06
     substance
    -0.06
    POSITIVE LOGITS
    ,mid
    0.08
    /pr
    0.06
     turb
    0.06
     gaan
    0.06
     topLevel
    0.06
    .uf
    0.06
     vd
    0.06
     filmer
    0.06
    obby
    0.06
     cara
    0.06
    Act Density 0.009%

    No Known Activations