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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .float
    -0.07
     phen
    -0.06
    reload
    -0.06
     Foundation
    -0.06
    _)
↵
    -0.06
     sliced
    -0.06
     characteristics
    -0.06
    ців
    -0.06
    iom
    -0.06
    -wing
    -0.06
    POSITIVE LOGITS
     pł
    0.07
    办理
    0.07
     lái
    0.07
     обрат
    0.07
    HDATA
    0.06
    CHEMY
    0.06
     началь
    0.06
     Kimber
    0.06
    ลำ
    0.06
     Herc
    0.06
    Act Density 0.031%

    No Known Activations