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

    Neuronpedia

    INDEX
    Explanations

    organizational development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    frmt
    0.46
    romechanical
    0.46
     బి
    0.45
    estimated
    0.43
    cans
    0.43
    षित
    0.43
    <0x9B>
    0.42
    相应
    0.42
    andas
    0.42
    ons
    0.42
    POSITIVE LOGITS
    યો
    0.47
    Ле
    0.46
    酆
    0.45
    이크
    0.45
     dilute
    0.44
    겅
    0.43
     Geschichte
    0.43
     diretor
    0.43
     depress
    0.42
    Пер
    0.42
    Act Density 0.000%

    No Known Activations