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

    Neuronpedia

    INDEX
    Explanations

    β

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     umož
    -0.07
     zahl
    -0.07
     Romania
    -0.07
    έντρο
    -0.07
     cocaine
    -0.07
     paved
    -0.07
    awei
    -0.07
    Prof
    -0.06
     isize
    -0.06
    .metrics
    -0.06
    POSITIVE LOGITS
     rebate
    0.07
    -<?
    0.06
     bal
    0.06
     ab
    0.06
     نسبة
    0.06
     sess
    0.06
     vak
    0.06
    available
    0.06
    -ab
    0.06
    b
    0.06
    Act Density 0.002%

    No Known Activations