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

    Neuronpedia

    INDEX
    Explanations

    Hawaiian culture/food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rewards
    -0.07
     supportive
    -0.07
     progression
    -0.06
    Tree
    -0.06
     equipment
    -0.06
    CAC
    -0.06
    .Par
    -0.06
     divergence
    -0.06
     presidents
    -0.06
    Foundation
    -0.06
    POSITIVE LOGITS
     writeTo
    0.08
     Lesser
    0.07
     PTR
    0.07
    FormData
    0.07
     mất
    0.07
    /column
    0.06
     Luc
    0.06
    isclosed
    0.06
     SAND
    0.06
    ritel
    0.06
    Act Density 0.003%

    No Known Activations