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

    Neuronpedia

    INDEX
    Explanations

    rules, laws, prohibitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IsPlainOldData
    -0.07
     delights
    -0.07
     rifle
    -0.07
     layers
    -0.07
     rifles
    -0.06
    획
    -0.06
    메
    -0.06
     /*
↵
    -0.06
     foods
    -0.06
     ==>
    -0.06
    POSITIVE LOGITS
    apsed
    0.07
    -through
    0.06
    ferred
    0.06
    PLACE
    0.06
    (heap
    0.06
     Airbnb
    0.06
    _COMPLETED
    0.06
    .Vertical
    0.06
    .visual
    0.06
     Nar
    0.06
    Act Density 0.048%

    No Known Activations