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

    Neuronpedia

    INDEX
    Explanations

    webkit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pag
    -0.07
     premiums
    -0.06
    ^[
    -0.06
    Equipment
    -0.06
     ‘
    -0.06
    Facade
    -0.05
     recruited
    -0.05
    -अ
    -0.05
    콘
    -0.05
     onCancel
    -0.05
    POSITIVE LOGITS
     Mitch
    0.07
    Mitch
    0.07
    Dick
    0.07
     crying
    0.06
    km
    0.06
    AIT
    0.06
     exploding
    0.06
     результат
    0.06
    ้อน
    0.06
    ़
    0.06
    Act Density 0.001%

    No Known Activations