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

    Neuronpedia

    INDEX
    Explanations

    é

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Docs
    -0.07
    (copy
    -0.06
     э
    -0.06
     اع
    -0.06
     memories
    -0.06
     Transition
    -0.06
     Ripple
    -0.06
     سوم
    -0.06
     BX
    -0.06
    >v
    -0.06
    POSITIVE LOGITS
     accus
    0.07
    INCLUDING
    0.06
    NULL
    0.06
    Calcul
    0.06
    owering
    0.06
    _opt
    0.06
     Judge
    0.06
    ounge
    0.06
    sthrough
    0.06
    ILA
    0.06
    Act Density 0.115%

    No Known Activations