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

    Neuronpedia

    INDEX
    Explanations

    "as well"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DLC
    -0.08
     Kov
    -0.07
    ♁
    -0.07
     TAB
    -0.07
     FEC
    -0.06
    リング
    -0.06
    キング
    -0.06
     MONEY
    -0.06
    RV
    -0.06
     OCT
    -0.06
    POSITIVE LOGITS
    .intent
    0.08
    䏝
    0.07
     expenses
    0.07
    中途
    0.07
     contaminated
    0.07
    忽
    0.06
    .home
    0.06
    .tabs
    0.06
    ╄
    0.06
    迕
    0.06
    Act Density 0.251%

    No Known Activations