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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roleId
    -0.08
    fair
    -0.07
    \Backend
    -0.07
     isAdmin
    -0.07
    에서는
    -0.07
     etree
    -0.07
     panties
    -0.06
     sweater
    -0.06
    ơn
    -0.06
    tadır
    -0.06
    POSITIVE LOGITS
    幾
    0.07
     Investments
    0.07
     positioning
    0.06
     applications
    0.06
     Applications
    0.06
     manages
    0.06
    .friends
    0.06
    Jeremy
    0.06
    _A
    0.06
    _jump
    0.06
    Act Density 0.013%

    No Known Activations