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

    Neuronpedia

    INDEX
    Explanations

    handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repression
    -0.06
    atori
    -0.06
    ัช
    -0.06
     ancora
    -0.06
    ère
    -0.06
    >>::
    -0.06
    Boxes
    -0.06
     footage
    -0.06
     ран
    -0.06
    RIORITY
    -0.05
    POSITIVE LOGITS
     handling
    0.08
     acquisitions
    0.07
    Additionally
    0.07
     reactive
    0.06
    ovaná
    0.06
     serviços
    0.06
     Became
    0.06
    Forgery
    0.06
     Jaime
    0.06
     sacrifice
    0.06
    Act Density 0.010%

    No Known Activations