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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uf
    -0.07
    엠
    -0.07
     Submit
    -0.07
     Vik
    -0.07
     domic
    -0.07
    nip
    -0.07
    ,ep
    -0.07
     кроме
    -0.07
    送达
    -0.07
     delve
    -0.07
    POSITIVE LOGITS
    .variable
    0.08
     escal
    0.07
    中药
    0.07
    链条
    0.07
    均衡
    0.07
     bladder
    0.07
     algo
    0.07
     Translation
    0.07
     suggest
    0.07
    compan
    0.06
    Act Density 0.003%

    No Known Activations