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

    Neuronpedia

    INDEX
    Explanations

    emissions reduction percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đổi
    -0.08
     GRE
    -0.07
    แป
    -0.07
     Attach
    -0.06
    Giving
    -0.06
    SPEC
    -0.06
    mens
    -0.06
    ทอง
    -0.06
     '?'
    -0.06
    Alloc
    -0.06
    POSITIVE LOGITS
    earchBar
    0.06
     LSM
    0.06
    InterfaceOrientation
    0.06
    .setColumn
    0.06
    емо
    0.06
     دس
    0.06
    ्त
    0.06
     massac
    0.06
    _scheduler
    0.05
    Resultado
    0.05
    Act Density 0.017%

    No Known Activations